Incremental gradient method for Karcher mean onsymmetric cones
Sangho Kum and Sangwoon Yun
Department of Mathematics EducationChungbuk National University
2016 MAO (Workshop on Matrices and Operator)
July 5, 2016
Suites Hotel, Jeju
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 1 / 32
1. Riemannian center of mass or Karcher mean
A brief history
Definition 1. (Riemannian center of mass)
(M, d): an n-dimensional complete Riemannian manifold withdistance d induced by the Riemannian structure.
ν : a probability measure on M.
f2(x) =1
2
∫d2(x , s)dν(s).
Any minimizer of f2 is called a Riemannian L2 center of mass withrespect to ν.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 2 / 32
1. Riemannian center of mass or Karcher mean
A brief history
Definition 1. (Riemannian center of mass)
(M, d): an n-dimensional complete Riemannian manifold withdistance d induced by the Riemannian structure.
ν : a probability measure on M.
f2(x) =1
2
∫d2(x , s)dν(s).
Any minimizer of f2 is called a Riemannian L2 center of mass withrespect to ν.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 2 / 32
1. Riemannian center of mass or Karcher mean
A brief history
Definition 1. (Riemannian center of mass)
(M, d): an n-dimensional complete Riemannian manifold withdistance d induced by the Riemannian structure.
ν : a probability measure on M.
f2(x) =1
2
∫d2(x , s)dν(s).
Any minimizer of f2 is called a Riemannian L2 center of mass withrespect to ν.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 2 / 32
1. Riemannian center of mass or Karcher mean
A brief history
Definition 1. (Riemannian center of mass)
(M, d): an n-dimensional complete Riemannian manifold withdistance d induced by the Riemannian structure.
ν : a probability measure on M.
f2(x) =1
2
∫d2(x , s)dν(s).
Any minimizer of f2 is called a Riemannian L2 center of mass withrespect to ν.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 2 / 32
1. Riemannian center of mass or Karcher mean
A brief history
Definition 1. (Riemannian center of mass)
(M, d): an n-dimensional complete Riemannian manifold withdistance d induced by the Riemannian structure.
ν : a probability measure on M.
f2(x) =1
2
∫d2(x , s)dν(s).
Any minimizer of f2 is called a Riemannian L2 center of mass withrespect to ν.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 2 / 32
1. Riemannian center of mass or Karcher mean
E. Cartan : In 1920s, the Riemannian L2 center of mass in anHadamard manifold (the first one in the context of Riemanniangeometry)
Existence and Uniqueness.
Any compact subgroup of the isometry group of an Hadamardmanifold has a fixed point.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 3 / 32
1. Riemannian center of mass or Karcher mean
E. Cartan : In 1920s, the Riemannian L2 center of mass in anHadamard manifold (the first one in the context of Riemanniangeometry)
Existence and Uniqueness.
Any compact subgroup of the isometry group of an Hadamardmanifold has a fixed point.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 3 / 32
1. Riemannian center of mass or Karcher mean
E. Cartan : In 1920s, the Riemannian L2 center of mass in anHadamard manifold (the first one in the context of Riemanniangeometry)
Existence and Uniqueness.
Any compact subgroup of the isometry group of an Hadamardmanifold has a fixed point.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 3 / 32
1. Riemannian center of mass or Karcher mean
E. Cartan : In 1920s, the Riemannian L2 center of mass in anHadamard manifold (the first one in the context of Riemanniangeometry)
Existence and Uniqueness.
Any compact subgroup of the isometry group of an Hadamardmanifold has a fixed point.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 3 / 32
1. Riemannian center of mass or Karcher mean
H. Karcher : The Riemannian L2 center of mass in generalRiemannian manifolds but for probability measures with support insmall enough balls
He enlarged the domain of existence and uniqueness and considerednew applications.
More recently, the Karcher mean has found applications in manyapplied fields:
computer vision, statistical analysis of shapes, medical imaging,sensor networks, data analysis applications, and so an.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 4 / 32
1. Riemannian center of mass or Karcher mean
H. Karcher : The Riemannian L2 center of mass in generalRiemannian manifolds but for probability measures with support insmall enough balls
He enlarged the domain of existence and uniqueness and considerednew applications.
More recently, the Karcher mean has found applications in manyapplied fields:
computer vision, statistical analysis of shapes, medical imaging,sensor networks, data analysis applications, and so an.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 4 / 32
1. Riemannian center of mass or Karcher mean
H. Karcher : The Riemannian L2 center of mass in generalRiemannian manifolds but for probability measures with support insmall enough balls
He enlarged the domain of existence and uniqueness and considerednew applications.
More recently, the Karcher mean has found applications in manyapplied fields:
computer vision, statistical analysis of shapes, medical imaging,sensor networks, data analysis applications, and so an.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 4 / 32
1. Riemannian center of mass or Karcher mean
H. Karcher : The Riemannian L2 center of mass in generalRiemannian manifolds but for probability measures with support insmall enough balls
He enlarged the domain of existence and uniqueness and considerednew applications.
More recently, the Karcher mean has found applications in manyapplied fields:
computer vision, statistical analysis of shapes, medical imaging,sensor networks, data analysis applications, and so an.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 4 / 32
1. Riemannian center of mass or Karcher mean
H. Karcher : The Riemannian L2 center of mass in generalRiemannian manifolds but for probability measures with support insmall enough balls
He enlarged the domain of existence and uniqueness and considerednew applications.
More recently, the Karcher mean has found applications in manyapplied fields:
computer vision, statistical analysis of shapes, medical imaging,sensor networks, data analysis applications, and so an.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 4 / 32
1. Riemannian center of mass or Karcher mean
Existing methodologies
In these applied settings, an important problem is to numericallyapproximate or compute the Karcher mean.
Gradient descent methods
Proximal point methods(or incremental proximal methods)
Newton methods
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 5 / 32
1. Riemannian center of mass or Karcher mean
Existing methodologies
In these applied settings, an important problem is to numericallyapproximate or compute the Karcher mean.
Gradient descent methods
Proximal point methods(or incremental proximal methods)
Newton methods
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 5 / 32
1. Riemannian center of mass or Karcher mean
Existing methodologies
In these applied settings, an important problem is to numericallyapproximate or compute the Karcher mean.
Gradient descent methods
Proximal point methods(or incremental proximal methods)
Newton methods
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 5 / 32
1. Riemannian center of mass or Karcher mean
Existing methodologies
In these applied settings, an important problem is to numericallyapproximate or compute the Karcher mean.
Gradient descent methods
Proximal point methods(or incremental proximal methods)
Newton methods
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 5 / 32
1. Riemannian center of mass or Karcher mean
Existing methodologies
In these applied settings, an important problem is to numericallyapproximate or compute the Karcher mean.
Gradient descent methods
Proximal point methods(or incremental proximal methods)
Newton methods
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 5 / 32
1. Riemannian center of mass or Karcher mean
Existing methodologies
In these applied settings, an important problem is to numericallyapproximate or compute the Karcher mean.
Gradient descent methods
Proximal point methods(or incremental proximal methods)
Newton methods
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 5 / 32
1. Riemannian center of mass or Karcher mean
Points to consider
But, even though numerical algorithms were developed in generalRiemannian manifolds circumstances or more, some of them are notnumerically implementable in a practical sense.
It is quite often that algorithms on Riemannian manifolds seem to beconceptual when we consider that applications are mainlyconcentrated on matrix cases.
In comparison to this, to develop algorithms is more tangible insymmetric cone settings as in the case of the positive semidefinitecone.
This is a main reason why we work under the framework of symmetriccones.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 6 / 32
1. Riemannian center of mass or Karcher mean
Points to consider
But, even though numerical algorithms were developed in generalRiemannian manifolds circumstances or more, some of them are notnumerically implementable in a practical sense.
It is quite often that algorithms on Riemannian manifolds seem to beconceptual when we consider that applications are mainlyconcentrated on matrix cases.
In comparison to this, to develop algorithms is more tangible insymmetric cone settings as in the case of the positive semidefinitecone.
This is a main reason why we work under the framework of symmetriccones.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 6 / 32
1. Riemannian center of mass or Karcher mean
Points to consider
But, even though numerical algorithms were developed in generalRiemannian manifolds circumstances or more, some of them are notnumerically implementable in a practical sense.
It is quite often that algorithms on Riemannian manifolds seem to beconceptual when we consider that applications are mainlyconcentrated on matrix cases.
In comparison to this, to develop algorithms is more tangible insymmetric cone settings as in the case of the positive semidefinitecone.
This is a main reason why we work under the framework of symmetriccones.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 6 / 32
1. Riemannian center of mass or Karcher mean
Points to consider
But, even though numerical algorithms were developed in generalRiemannian manifolds circumstances or more, some of them are notnumerically implementable in a practical sense.
It is quite often that algorithms on Riemannian manifolds seem to beconceptual when we consider that applications are mainlyconcentrated on matrix cases.
In comparison to this, to develop algorithms is more tangible insymmetric cone settings as in the case of the positive semidefinitecone.
This is a main reason why we work under the framework of symmetriccones.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 6 / 32
1. Riemannian center of mass or Karcher mean
Points to consider
But, even though numerical algorithms were developed in generalRiemannian manifolds circumstances or more, some of them are notnumerically implementable in a practical sense.
It is quite often that algorithms on Riemannian manifolds seem to beconceptual when we consider that applications are mainlyconcentrated on matrix cases.
In comparison to this, to develop algorithms is more tangible insymmetric cone settings as in the case of the positive semidefinitecone.
This is a main reason why we work under the framework of symmetriccones.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 6 / 32
1. Riemannian center of mass or Karcher mean
Jordan algebra
A Jordan algebra V over R is a (non-associative) commutativealgebra satisfying x2(xy) = x(x2y) for all x , y ∈ V .
For x ∈ V , let L(x) be the linear operator defined by L(x)y = xy , andlet P(x) = 2L(x)2 − L(x2). The map P is called the quadraticrepresentation of V .
An element x ∈ V is said to be invertible if there exists an element y(denoted by y = x−1) in the subalgebra generated by x and e (theJordan identity) such that xy = e.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 7 / 32
1. Riemannian center of mass or Karcher mean
Jordan algebra
A Jordan algebra V over R is a (non-associative) commutativealgebra satisfying x2(xy) = x(x2y) for all x , y ∈ V .
For x ∈ V , let L(x) be the linear operator defined by L(x)y = xy , andlet P(x) = 2L(x)2 − L(x2). The map P is called the quadraticrepresentation of V .
An element x ∈ V is said to be invertible if there exists an element y(denoted by y = x−1) in the subalgebra generated by x and e (theJordan identity) such that xy = e.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 7 / 32
1. Riemannian center of mass or Karcher mean
Jordan algebra
A Jordan algebra V over R is a (non-associative) commutativealgebra satisfying x2(xy) = x(x2y) for all x , y ∈ V .
For x ∈ V , let L(x) be the linear operator defined by L(x)y = xy , andlet P(x) = 2L(x)2 − L(x2). The map P is called the quadraticrepresentation of V .
An element x ∈ V is said to be invertible if there exists an element y(denoted by y = x−1) in the subalgebra generated by x and e (theJordan identity) such that xy = e.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 7 / 32
1. Riemannian center of mass or Karcher mean
Jordan algebra
A Jordan algebra V over R is a (non-associative) commutativealgebra satisfying x2(xy) = x(x2y) for all x , y ∈ V .
For x ∈ V , let L(x) be the linear operator defined by L(x)y = xy , andlet P(x) = 2L(x)2 − L(x2). The map P is called the quadraticrepresentation of V .
An element x ∈ V is said to be invertible if there exists an element y(denoted by y = x−1) in the subalgebra generated by x and e (theJordan identity) such that xy = e.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 7 / 32
1. Riemannian center of mass or Karcher mean
Euclidean Jordan algebra (finite dim′l symmetric cone)
A finite dimensional Jordan algebra V is said to be Euclidean if thereexists an inner product 〈·, ·〉 such that
〈xy , z〉 = 〈y , xz〉 (1.1)
for all x , y , z ∈ V .
An element c ∈ V is called an idempotent if c2 = c. We say thatc1, . . . , ck is a complete system of orthogonal idempotents ifc2i = ci , cicj = 0, i 6= j , c1 + · · ·+ ck = e. An idempotent is primitive
if it is non-zero and cannot be written as the sum of two non-zeroidempotents. A Jordan frame is a complete system of primitiveidempotents.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 8 / 32
1. Riemannian center of mass or Karcher mean
Euclidean Jordan algebra (finite dim′l symmetric cone)
A finite dimensional Jordan algebra V is said to be Euclidean if thereexists an inner product 〈·, ·〉 such that
〈xy , z〉 = 〈y , xz〉 (1.1)
for all x , y , z ∈ V .
An element c ∈ V is called an idempotent if c2 = c. We say thatc1, . . . , ck is a complete system of orthogonal idempotents ifc2i = ci , cicj = 0, i 6= j , c1 + · · ·+ ck = e. An idempotent is primitive
if it is non-zero and cannot be written as the sum of two non-zeroidempotents. A Jordan frame is a complete system of primitiveidempotents.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 8 / 32
1. Riemannian center of mass or Karcher mean
Euclidean Jordan algebra (finite dim′l symmetric cone)
A finite dimensional Jordan algebra V is said to be Euclidean if thereexists an inner product 〈·, ·〉 such that
〈xy , z〉 = 〈y , xz〉 (1.1)
for all x , y , z ∈ V .
An element c ∈ V is called an idempotent if c2 = c. We say thatc1, . . . , ck is a complete system of orthogonal idempotents ifc2i = ci , cicj = 0, i 6= j , c1 + · · ·+ ck = e. An idempotent is primitive
if it is non-zero and cannot be written as the sum of two non-zeroidempotents. A Jordan frame is a complete system of primitiveidempotents.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 8 / 32
1. Riemannian center of mass or Karcher mean
Let Q be the set of all square elements of V . Then Q is a closedconvex cone of V with Q ∩ −Q = 0, and is the set of elementx ∈ V such that L(x) is positive semi-definite.
It turns out that Q has non-empty interior Ω, and Ω is a symmetriccone, that is, the group
G (Ω) = g ∈ GL(V )|g(Ω) = Ω
acts transitively on it and Ω is a self-dual cone with respect to theinner product 〈·|·〉.
Furthermore, for any a in Ω, P(a) ∈ G (Ω) and is positive definite.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 9 / 32
1. Riemannian center of mass or Karcher mean
Let Q be the set of all square elements of V . Then Q is a closedconvex cone of V with Q ∩ −Q = 0, and is the set of elementx ∈ V such that L(x) is positive semi-definite.
It turns out that Q has non-empty interior Ω, and Ω is a symmetriccone, that is, the group
G (Ω) = g ∈ GL(V )|g(Ω) = Ω
acts transitively on it and Ω is a self-dual cone with respect to theinner product 〈·|·〉.
Furthermore, for any a in Ω, P(a) ∈ G (Ω) and is positive definite.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 9 / 32
1. Riemannian center of mass or Karcher mean
Let Q be the set of all square elements of V . Then Q is a closedconvex cone of V with Q ∩ −Q = 0, and is the set of elementx ∈ V such that L(x) is positive semi-definite.
It turns out that Q has non-empty interior Ω, and Ω is a symmetriccone, that is, the group
G (Ω) = g ∈ GL(V )|g(Ω) = Ω
acts transitively on it and Ω is a self-dual cone with respect to theinner product 〈·|·〉.
Furthermore, for any a in Ω, P(a) ∈ G (Ω) and is positive definite.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 9 / 32
1. Riemannian center of mass or Karcher mean
Two typical examples
Second-order cone(SOC) is the closed convex cone
K :=
(x1, x2) ∈ R× Rn−1 | ‖x2‖ ≤ x1
.
The Euclidean space Rn with the Jordan product defined by
x y = (〈x , y〉, x1y2 + y1x2)
is a Euclidean Jordan algebra equipped with the standard innerproduct 〈·, ·〉 where x = (x1, x2), y = (y1, y2) ∈ R× Rn−1.
K is the corresponding symmetric cone of the Euclidean Jordanalgebra Rn.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 10 / 32
1. Riemannian center of mass or Karcher mean
Two typical examples
Second-order cone(SOC) is the closed convex cone
K :=
(x1, x2) ∈ R× Rn−1 | ‖x2‖ ≤ x1
.
The Euclidean space Rn with the Jordan product defined by
x y = (〈x , y〉, x1y2 + y1x2)
is a Euclidean Jordan algebra equipped with the standard innerproduct 〈·, ·〉 where x = (x1, x2), y = (y1, y2) ∈ R× Rn−1.
K is the corresponding symmetric cone of the Euclidean Jordanalgebra Rn.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 10 / 32
1. Riemannian center of mass or Karcher mean
Two typical examples
Second-order cone(SOC) is the closed convex cone
K :=
(x1, x2) ∈ R× Rn−1 | ‖x2‖ ≤ x1
.
The Euclidean space Rn with the Jordan product defined by
x y = (〈x , y〉, x1y2 + y1x2)
is a Euclidean Jordan algebra equipped with the standard innerproduct 〈·, ·〉 where x = (x1, x2), y = (y1, y2) ∈ R× Rn−1.
K is the corresponding symmetric cone of the Euclidean Jordanalgebra Rn.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 10 / 32
1. Riemannian center of mass or Karcher mean
Two typical examples
Second-order cone(SOC) is the closed convex cone
K :=
(x1, x2) ∈ R× Rn−1 | ‖x2‖ ≤ x1
.
The Euclidean space Rn with the Jordan product defined by
x y = (〈x , y〉, x1y2 + y1x2)
is a Euclidean Jordan algebra equipped with the standard innerproduct 〈·, ·〉 where x = (x1, x2), y = (y1, y2) ∈ R× Rn−1.
K is the corresponding symmetric cone of the Euclidean Jordanalgebra Rn.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 10 / 32
1. Riemannian center of mass or Karcher mean
Let Sn be the algebra of n × n real symmetric matrices with theJordan product defined by
X Y =XY + YX
2
where XY is the usual matrix multiplication of X and Y .
Then Sn is a Euclidean Jordan algebra equipped with the trace innerproduct
〈X ,Y 〉 = tr(XY ), P(X )Y = XYX .
PD is the corresponding symmetric cone of the Euclidean Jordanalgebra Sn.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 11 / 32
1. Riemannian center of mass or Karcher mean
Let Sn be the algebra of n × n real symmetric matrices with theJordan product defined by
X Y =XY + YX
2
where XY is the usual matrix multiplication of X and Y .
Then Sn is a Euclidean Jordan algebra equipped with the trace innerproduct
〈X ,Y 〉 = tr(XY ), P(X )Y = XYX .
PD is the corresponding symmetric cone of the Euclidean Jordanalgebra Sn.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 11 / 32
1. Riemannian center of mass or Karcher mean
Let Sn be the algebra of n × n real symmetric matrices with theJordan product defined by
X Y =XY + YX
2
where XY is the usual matrix multiplication of X and Y .
Then Sn is a Euclidean Jordan algebra equipped with the trace innerproduct
〈X ,Y 〉 = tr(XY ), P(X )Y = XYX .
PD is the corresponding symmetric cone of the Euclidean Jordanalgebra Sn.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 11 / 32
1. Riemannian center of mass or Karcher mean
Symmetric cone setting
The symmetric cone Ω admits a Riemannian metric defined by
〈u, v〉x = 〈P(x)−1u, v〉, x ∈ Ω, u, v ∈ V .
The Riemannian distance δ(a, b) is given by
δ(a, b) == ‖ log P(a−12 )b‖ =
(r∑
i=1
log2 λi (P(a−1/2)b)
)1/2
.
The unique geodesic curve joining a and b is
t 7→ a#tb := P(a1/2)(P(a−1/2)b)t .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 12 / 32
1. Riemannian center of mass or Karcher mean
Symmetric cone setting
The symmetric cone Ω admits a Riemannian metric defined by
〈u, v〉x = 〈P(x)−1u, v〉, x ∈ Ω, u, v ∈ V .
The Riemannian distance δ(a, b) is given by
δ(a, b) == ‖ log P(a−12 )b‖ =
(r∑
i=1
log2 λi (P(a−1/2)b)
)1/2
.
The unique geodesic curve joining a and b is
t 7→ a#tb := P(a1/2)(P(a−1/2)b)t .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 12 / 32
1. Riemannian center of mass or Karcher mean
Symmetric cone setting
The symmetric cone Ω admits a Riemannian metric defined by
〈u, v〉x = 〈P(x)−1u, v〉, x ∈ Ω, u, v ∈ V .
The Riemannian distance δ(a, b) is given by
δ(a, b) == ‖ log P(a−12 )b‖ =
(r∑
i=1
log2 λi (P(a−1/2)b)
)1/2
.
The unique geodesic curve joining a and b is
t 7→ a#tb := P(a1/2)(P(a−1/2)b)t .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 12 / 32
1. Riemannian center of mass or Karcher mean
Symmetric cone setting
The symmetric cone Ω admits a Riemannian metric defined by
〈u, v〉x = 〈P(x)−1u, v〉, x ∈ Ω, u, v ∈ V .
The Riemannian distance δ(a, b) is given by
δ(a, b) == ‖ log P(a−12 )b‖ =
(r∑
i=1
log2 λi (P(a−1/2)b)
)1/2
.
The unique geodesic curve joining a and b is
t 7→ a#tb := P(a1/2)(P(a−1/2)b)t .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 12 / 32
1. Riemannian center of mass or Karcher mean
An important property of the metric δ is the semiparallelogram law
δ2(z , x#y) ≤ 1
2δ2(z , x) +
1
2δ2(z , y)− 1
4δ2(x , y)
and its general form for any t ∈ [0, 1]
δ2(z , x#ty) ≤ (1− t)δ2(z , x) + tδ2(z , y)− t(1− t)δ2(x , y).
The Riemannian manifold (Ω, δ) is an important example of anHadamard manifold.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 13 / 32
1. Riemannian center of mass or Karcher mean
An important property of the metric δ is the semiparallelogram law
δ2(z , x#y) ≤ 1
2δ2(z , x) +
1
2δ2(z , y)− 1
4δ2(x , y)
and its general form for any t ∈ [0, 1]
δ2(z , x#ty) ≤ (1− t)δ2(z , x) + tδ2(z , y)− t(1− t)δ2(x , y).
The Riemannian manifold (Ω, δ) is an important example of anHadamard manifold.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 13 / 32
1. Riemannian center of mass or Karcher mean
In this circumstances, the Karcher mean reduces to the following:
Definition 2. (Karcher mean in symmetric cones)
The Karcher mean of a1, . . . , an ∈ Ω is defined to be the unique minimizerof the sum of squares of the Riemannian distances to each of the ai , i.e.,
Λ(a1, . . . , an) = argminx∈Ω
1
2
n∑i=1
δ2(x , ai ).
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 14 / 32
1. Riemannian center of mass or Karcher mean
In this circumstances, the Karcher mean reduces to the following:
Definition 2. (Karcher mean in symmetric cones)
The Karcher mean of a1, . . . , an ∈ Ω is defined to be the unique minimizerof the sum of squares of the Riemannian distances to each of the ai , i.e.,
Λ(a1, . . . , an) = argminx∈Ω
1
2
n∑i=1
δ2(x , ai ).
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 14 / 32
1. Riemannian center of mass or Karcher mean
In this circumstances, the Karcher mean reduces to the following:
Definition 2. (Karcher mean in symmetric cones)
The Karcher mean of a1, . . . , an ∈ Ω is defined to be the unique minimizerof the sum of squares of the Riemannian distances to each of the ai , i.e.,
Λ(a1, . . . , an) = argminx∈Ω
1
2
n∑i=1
δ2(x , ai ).
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 14 / 32
2. Motivation and Problem formulation
Motivations
The objective function of the aforementioned minimization problem isthe sum of many functions, i.e., the squares of Riemannian distancefunctions with given data a1, . . . , an ∈ Ω:
minx∈Ω
f (x) :=m∑i=1
fi (x), (2.1)
where fi (x) = 12δ(x , ai )
2 with ai ’s and x in Ω.
It is observed that the solution of the problem belongs to a boundedset D = x ∈ Ω | αe ≤ x ≤ βe, where 0 < α ≤ β, that containsa1, . . . , an.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 15 / 32
2. Motivation and Problem formulation
Motivations
The objective function of the aforementioned minimization problem isthe sum of many functions, i.e., the squares of Riemannian distancefunctions with given data a1, . . . , an ∈ Ω:
minx∈Ω
f (x) :=m∑i=1
fi (x), (2.1)
where fi (x) = 12δ(x , ai )
2 with ai ’s and x in Ω.
It is observed that the solution of the problem belongs to a boundedset D = x ∈ Ω | αe ≤ x ≤ βe, where 0 < α ≤ β, that containsa1, . . . , an.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 15 / 32
2. Motivation and Problem formulation
Motivations
The objective function of the aforementioned minimization problem isthe sum of many functions, i.e., the squares of Riemannian distancefunctions with given data a1, . . . , an ∈ Ω:
minx∈Ω
f (x) :=m∑i=1
fi (x), (2.1)
where fi (x) = 12δ(x , ai )
2 with ai ’s and x in Ω.
It is observed that the solution of the problem belongs to a boundedset D = x ∈ Ω | αe ≤ x ≤ βe, where 0 < α ≤ β, that containsa1, . . . , an.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 15 / 32
2. Motivation and Problem formulation
Motivations
The objective function of the aforementioned minimization problem isthe sum of many functions, i.e., the squares of Riemannian distancefunctions with given data a1, . . . , an ∈ Ω:
minx∈Ω
f (x) :=m∑i=1
fi (x), (2.1)
where fi (x) = 12δ(x , ai )
2 with ai ’s and x in Ω.
It is observed that the solution of the problem belongs to a boundedset D = x ∈ Ω | αe ≤ x ≤ βe, where 0 < α ≤ β, that containsa1, . . . , an.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 15 / 32
2. Motivation and Problem formulation
Problem formulation
Thus, we consider the following bound constained minimizationproblem formulation of :
minx∈D
f (x). (2.2)
This problem formulation motivates us to adapt an incrementallyupdated gradient(IUG) method to solve the problem.
To our knowledge, this IUG method is not adopted to deal with theproblem of finding the Karcher mean yet.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 16 / 32
2. Motivation and Problem formulation
Problem formulation
Thus, we consider the following bound constained minimizationproblem formulation of :
minx∈D
f (x). (2.2)
This problem formulation motivates us to adapt an incrementallyupdated gradient(IUG) method to solve the problem.
To our knowledge, this IUG method is not adopted to deal with theproblem of finding the Karcher mean yet.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 16 / 32
2. Motivation and Problem formulation
Problem formulation
Thus, we consider the following bound constained minimizationproblem formulation of :
minx∈D
f (x). (2.2)
This problem formulation motivates us to adapt an incrementallyupdated gradient(IUG) method to solve the problem.
To our knowledge, this IUG method is not adopted to deal with theproblem of finding the Karcher mean yet.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 16 / 32
2. Motivation and Problem formulation
Problem formulation
Thus, we consider the following bound constained minimizationproblem formulation of :
minx∈D
f (x). (2.2)
This problem formulation motivates us to adapt an incrementallyupdated gradient(IUG) method to solve the problem.
To our knowledge, this IUG method is not adopted to deal with theproblem of finding the Karcher mean yet.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 16 / 32
3. Incrementally updated gradient(IUG) method
Incremental gradient(IG) method
In the case that the number of fi ’s consisting of the objective functionf =
∑ni=1 fi is large, traditional gradient method would be inefficient
since they require evaluating all the gradients of fi ’s before updatingthe iterate.
Incremental gradient methods, in contrast, update the iterate afterevaluation of gradients for only one or a few smooth functions.
Blatt et al. proposed a method that computes the gradient of a singlecomponent function at each iteration, but instead of updating theiterate using this gradient, it uses the sum of n most recentlycomputed gradients for the unconstrained smooth minimization case.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 17 / 32
3. Incrementally updated gradient(IUG) method
Incremental gradient(IG) method
In the case that the number of fi ’s consisting of the objective functionf =
∑ni=1 fi is large, traditional gradient method would be inefficient
since they require evaluating all the gradients of fi ’s before updatingthe iterate.
Incremental gradient methods, in contrast, update the iterate afterevaluation of gradients for only one or a few smooth functions.
Blatt et al. proposed a method that computes the gradient of a singlecomponent function at each iteration, but instead of updating theiterate using this gradient, it uses the sum of n most recentlycomputed gradients for the unconstrained smooth minimization case.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 17 / 32
3. Incrementally updated gradient(IUG) method
Incremental gradient(IG) method
In the case that the number of fi ’s consisting of the objective functionf =
∑ni=1 fi is large, traditional gradient method would be inefficient
since they require evaluating all the gradients of fi ’s before updatingthe iterate.
Incremental gradient methods, in contrast, update the iterate afterevaluation of gradients for only one or a few smooth functions.
Blatt et al. proposed a method that computes the gradient of a singlecomponent function at each iteration, but instead of updating theiterate using this gradient, it uses the sum of n most recentlycomputed gradients for the unconstrained smooth minimization case.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 17 / 32
3. Incrementally updated gradient(IUG) method
Incremental gradient(IG) method
In the case that the number of fi ’s consisting of the objective functionf =
∑ni=1 fi is large, traditional gradient method would be inefficient
since they require evaluating all the gradients of fi ’s before updatingthe iterate.
Incremental gradient methods, in contrast, update the iterate afterevaluation of gradients for only one or a few smooth functions.
Blatt et al. proposed a method that computes the gradient of a singlecomponent function at each iteration, but instead of updating theiterate using this gradient, it uses the sum of n most recentlycomputed gradients for the unconstrained smooth minimization case.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 17 / 32
3. Incrementally updated gradient(IUG) method
Assuming the uniform boundedness and Lipschitz continuity of all thegradients of fi ’s as well as the uniqueness of a stationary point andpositive definiteness of Hessian of f at the stationary point, the globalconvergence of this method with a sufficiently small stepsize is shown.
Blatt’s method may be viewed as belonging to a general class ofgradient methods that update the gradients for only one or a few fi ’sat a time, which we call incrementally updated gradient(IUG) method.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 18 / 32
3. Incrementally updated gradient(IUG) method
Assuming the uniform boundedness and Lipschitz continuity of all thegradients of fi ’s as well as the uniqueness of a stationary point andpositive definiteness of Hessian of f at the stationary point, the globalconvergence of this method with a sufficiently small stepsize is shown.
Blatt’s method may be viewed as belonging to a general class ofgradient methods that update the gradients for only one or a few fi ’sat a time, which we call incrementally updated gradient(IUG) method.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 18 / 32
3. Incrementally updated gradient(IUG) method
IUG method
Recently, Tseng and Yun proposed two IUG methods to solve thenonsmooth minimization problem whose objective is the sum of nsmooth functions and a convex function. They showed the globalconvergence for the IUG method using a constant step size, assumingonly the Lipschitz continuity of each gradient of n smooth functions.
Compared to Blatt’s one, IUG method is a more general one forsolving a more general problem, and the global convergence is shownunder much weaker assumptions.
The second IUG method uses adaptive stepsizes and hence morepractical, and it has a similar global convergence property as the firstIUG method.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 19 / 32
3. Incrementally updated gradient(IUG) method
IUG method
Recently, Tseng and Yun proposed two IUG methods to solve thenonsmooth minimization problem whose objective is the sum of nsmooth functions and a convex function. They showed the globalconvergence for the IUG method using a constant step size, assumingonly the Lipschitz continuity of each gradient of n smooth functions.
Compared to Blatt’s one, IUG method is a more general one forsolving a more general problem, and the global convergence is shownunder much weaker assumptions.
The second IUG method uses adaptive stepsizes and hence morepractical, and it has a similar global convergence property as the firstIUG method.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 19 / 32
3. Incrementally updated gradient(IUG) method
IUG method
Recently, Tseng and Yun proposed two IUG methods to solve thenonsmooth minimization problem whose objective is the sum of nsmooth functions and a convex function. They showed the globalconvergence for the IUG method using a constant step size, assumingonly the Lipschitz continuity of each gradient of n smooth functions.
Compared to Blatt’s one, IUG method is a more general one forsolving a more general problem, and the global convergence is shownunder much weaker assumptions.
The second IUG method uses adaptive stepsizes and hence morepractical, and it has a similar global convergence property as the firstIUG method.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 19 / 32
3. Incrementally updated gradient(IUG) method
IUG method
Recently, Tseng and Yun proposed two IUG methods to solve thenonsmooth minimization problem whose objective is the sum of nsmooth functions and a convex function. They showed the globalconvergence for the IUG method using a constant step size, assumingonly the Lipschitz continuity of each gradient of n smooth functions.
Compared to Blatt’s one, IUG method is a more general one forsolving a more general problem, and the global convergence is shownunder much weaker assumptions.
The second IUG method uses adaptive stepsizes and hence morepractical, and it has a similar global convergence property as the firstIUG method.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 19 / 32
3. Incrementally updated gradient(IUG) method
They generalized the previous IG method to handle constraints andnonsmooth regularization and proved the global convergence undermuch weaker assumptions.
For this IUG method, in the present paper, we work under thestandard framework of Euclidean spaces rather than Riemanniancircumstances from a theoretical viewpoint.
This is mainly due to the fact that an addition of vectors in differenttangent spaces of Riemannian manifolds is not possible. Even if itwere possible using a parallel transport, it may have no practicalmeaning in computation.
At present, it seems to be difficult to consider an effective IG methodin a fully Riemannian sense on a symmetric cone.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 20 / 32
4. IUG method for Karcher mean
IUG method for Karcher mean
The IUG method due to Tseng and Yun exactly fits to deal with theKarcher mean approximation (2.1) and (2.2) where the numbers ofthe smooth fi = 1
2δ(x , ai )2 is large.
The following fact plays a key role in the present work:
Proposition 1.
‖∇fi (y)−∇fi (z)‖ ≤ Li‖y − z‖ ∀y , z ∈ D, (4.1)
for some Li ≥ 0, i = 1, . . . ,m. Let L =∑m
i=1 Li .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 21 / 32
4. IUG method for Karcher mean
IUG method for Karcher mean
The IUG method due to Tseng and Yun exactly fits to deal with theKarcher mean approximation (2.1) and (2.2) where the numbers ofthe smooth fi = 1
2δ(x , ai )2 is large.
The following fact plays a key role in the present work:
Proposition 1.
‖∇fi (y)−∇fi (z)‖ ≤ Li‖y − z‖ ∀y , z ∈ D, (4.1)
for some Li ≥ 0, i = 1, . . . ,m. Let L =∑m
i=1 Li .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 21 / 32
4. IUG method for Karcher mean
IUG method for Karcher mean
The IUG method due to Tseng and Yun exactly fits to deal with theKarcher mean approximation (2.1) and (2.2) where the numbers ofthe smooth fi = 1
2δ(x , ai )2 is large.
The following fact plays a key role in the present work:
Proposition 1.
‖∇fi (y)−∇fi (z)‖ ≤ Li‖y − z‖ ∀y , z ∈ D, (4.1)
for some Li ≥ 0, i = 1, . . . ,m. Let L =∑m
i=1 Li .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 21 / 32
4. IUG method for Karcher mean
IUG method for Karcher mean
The IUG method due to Tseng and Yun exactly fits to deal with theKarcher mean approximation (2.1) and (2.2) where the numbers ofthe smooth fi = 1
2δ(x , ai )2 is large.
The following fact plays a key role in the present work:
Proposition 1.
‖∇fi (y)−∇fi (z)‖ ≤ Li‖y − z‖ ∀y , z ∈ D, (4.1)
for some Li ≥ 0, i = 1, . . . ,m. Let L =∑m
i=1 Li .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 21 / 32
4. IUG method for Karcher mean
IUG method for Karcher mean
The IUG method due to Tseng and Yun exactly fits to deal with theKarcher mean approximation (2.1) and (2.2) where the numbers ofthe smooth fi = 1
2δ(x , ai )2 is large.
The following fact plays a key role in the present work:
Proposition 1.
‖∇fi (y)−∇fi (z)‖ ≤ Li‖y − z‖ ∀y , z ∈ D, (4.1)
for some Li ≥ 0, i = 1, . . . ,m. Let L =∑m
i=1 Li .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 21 / 32
4. IUG method for Karcher mean
Moreover, we give an assumption as follows:
Assumption.
τki ≥ k − K for all i and k, where K ≥ 0 is an integer.
Assumption ensures that the gradient of fi is updated at least oncefor every K + 1 consecutive iterations.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 22 / 32
4. IUG method for Karcher mean
Moreover, we give an assumption as follows:
Assumption.
τki ≥ k − K for all i and k, where K ≥ 0 is an integer.
Assumption ensures that the gradient of fi is updated at least oncefor every K + 1 consecutive iterations.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 22 / 32
4. IUG method for Karcher mean
Moreover, we give an assumption as follows:
Assumption.
τki ≥ k − K for all i and k, where K ≥ 0 is an integer.
Assumption ensures that the gradient of fi is updated at least oncefor every K + 1 consecutive iterations.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 22 / 32
4. IUG method for Karcher mean
Algorithms
Algorithm 1.
Choose x0, x−1, · · · ∈ D and t ∈]0, 1]. Initialize k = 0. Update x (k+1)
from xk by the following template:
Step 1. Choose 0 ≤ τki ≤ k for i = 1, . . . ,m,
Step 2. Update gk by
gk =m∑i=1
∇fi (xτki ). (4.2)
Step 3. Find dk by using
dk = argmind∈V ,xk+d∈D
〈gk , d〉+
1
2‖d‖2
. (4.3)
Step 4. xk+1 = xk + tdk .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 23 / 32
4. IUG method for Karcher mean
Algorithms
Algorithm 1.
Choose x0, x−1, · · · ∈ D and t ∈]0, 1]. Initialize k = 0. Update x (k+1)
from xk by the following template:
Step 1. Choose 0 ≤ τki ≤ k for i = 1, . . . ,m,
Step 2. Update gk by
gk =m∑i=1
∇fi (xτki ). (4.2)
Step 3. Find dk by using
dk = argmind∈V ,xk+d∈D
〈gk , d〉+
1
2‖d‖2
. (4.3)
Step 4. xk+1 = xk + tdk .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 23 / 32
4. IUG method for Karcher mean
Algorithms
Algorithm 1.
Choose x0, x−1, · · · ∈ D and t ∈]0, 1]. Initialize k = 0. Update x (k+1)
from xk by the following template:
Step 1. Choose 0 ≤ τki ≤ k for i = 1, . . . ,m,
Step 2. Update gk by
gk =m∑i=1
∇fi (xτki ). (4.2)
Step 3. Find dk by using
dk = argmind∈V ,xk+d∈D
〈gk , d〉+
1
2‖d‖2
. (4.3)
Step 4. xk+1 = xk + tdk .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 23 / 32
4. IUG method for Karcher mean
The above framework is quite flexible and allows partiallyasynchronous updating of the component gradients.
In the following lemma, we give a descent property of theminimization subproblem (4.3) for finding a search direction.
Lemma 1.
For any x ∈ D, and g ∈ V , let dg be the solution of the problem
mind∈V ,x+d∈D
〈g , d〉+
1
2‖d‖2
.
Then
〈g , d〉+1
2‖d‖2 ≤ −1
2‖dg‖2 or 〈g , dg 〉 ≤ −‖dg‖2. (4.4)
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 24 / 32
4. IUG method for Karcher mean
The above framework is quite flexible and allows partiallyasynchronous updating of the component gradients.
In the following lemma, we give a descent property of theminimization subproblem (4.3) for finding a search direction.
Lemma 1.
For any x ∈ D, and g ∈ V , let dg be the solution of the problem
mind∈V ,x+d∈D
〈g , d〉+
1
2‖d‖2
.
Then
〈g , d〉+1
2‖d‖2 ≤ −1
2‖dg‖2 or 〈g , dg 〉 ≤ −‖dg‖2. (4.4)
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 24 / 32
4. IUG method for Karcher mean
The above framework is quite flexible and allows partiallyasynchronous updating of the component gradients.
In the following lemma, we give a descent property of theminimization subproblem (4.3) for finding a search direction.
Lemma 1.
For any x ∈ D, and g ∈ V , let dg be the solution of the problem
mind∈V ,x+d∈D
〈g , d〉+
1
2‖d‖2
.
Then
〈g , d〉+1
2‖d‖2 ≤ −1
2‖dg‖2 or 〈g , dg 〉 ≤ −‖dg‖2. (4.4)
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 24 / 32
4. IUG method for Karcher mean
An x ∈ V is a stationary point of f if x ∈ D and f ′(x ; d) ≥ 0 for alld ∈ V .
The following result characterizes stationarity in terms of d∇f (x).
Lemma 2.
An x ∈ D is a stationary point of f if and only if d∇f (x) = 0.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 25 / 32
4. IUG method for Karcher mean
An x ∈ V is a stationary point of f if x ∈ D and f ′(x ; d) ≥ 0 for alld ∈ V .
The following result characterizes stationarity in terms of d∇f (x).
Lemma 2.
An x ∈ D is a stationary point of f if and only if d∇f (x) = 0.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 25 / 32
4. IUG method for Karcher mean
Now, we have the following global convergence result for the methodwith a sufficiently small constant stepsize.
Theorem 1. (Constant Stepsize Case)
Let xk and dk be sequences generated by Algorithm 1 underAssumption, and with t < 2
L(2K+1) . Then dk → 0 and every cluster
point of xk is a stationary point.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 26 / 32
4. IUG method for Karcher mean
Now, we have the following global convergence result for the methodwith a sufficiently small constant stepsize.
Theorem 1. (Constant Stepsize Case)
Let xk and dk be sequences generated by Algorithm 1 underAssumption, and with t < 2
L(2K+1) . Then dk → 0 and every cluster
point of xk is a stationary point.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 26 / 32
4. IUG method for Karcher mean
We describe the second IG method with adaptive stepsize below.
Algorithm 2.
Choose x0, x−1, . . . ∈ D, t ∈]0, 1], β ∈]0, 1[, and σ > 12 . Initialize k = 0.
Update x (k+1) from xk by the following template:
Step 1. Choose 0 ≤ τki ≤ k for i = 1, . . . ,m,
Step 2. Update gk by (4.2)
Step 3. Find dk by using (4.3)
Step 4. Choose tinit
k ∈ [t, 1] and let tk be the largest element of
t init
k βjj=0,1,... satisfying
f (xk + tkdk)− f (xk) ≤ −σKL‖tkdk‖2 +L
2
k−1∑j=(k−K)+
‖tjd j‖2
(4.5)
Step 5. xk+1 = xk + tdk .
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 27 / 32
4. IUG method for Karcher mean
We describe the second IG method with adaptive stepsize below.
Algorithm 2.
Choose x0, x−1, . . . ∈ D, t ∈]0, 1], β ∈]0, 1[, and σ > 12 . Initialize k = 0.
Update x (k+1) from xk by the following template:
Step 1. Choose 0 ≤ τki ≤ k for i = 1, . . . ,m,
Step 2. Update gk by (4.2)
Step 3. Find dk by using (4.3)
Step 4. Choose tinit
k ∈ [t, 1] and let tk be the largest element of
t init
k βjj=0,1,... satisfying
f (xk + tkdk)− f (xk) ≤ −σKL‖tkdk‖2 +L
2
k−1∑j=(k−K)+
‖tjd j‖2
(4.5)
Step 5. xk+1 = xk + tdk .Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 27 / 32
4. IUG method for Karcher mean
The stepsize tk in the first IUG method is adaptively selected bydecreasing tk whenever the condition (4.5) is violated.
In practice, the Lipschitz constant L is not given a priori but we areable to estimate L by increasing L by a certain positive factorwhenever the condition (4.5) is not satisfied with starting at anarbitrary estimate of L.
When tk is below t defined in Theorem 2 below, the condition (4.5) issatisfied with some constant L. Whether L is defined by Proposition 1is irrelevant.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 28 / 32
4. IUG method for Karcher mean
Theorem 2. (Adaptive Stepsize Case)
Let xk, dk, tk be sequences generated by Algorithm 2 underAssumption 1. Then the following results hold.
(a) For each k ≥ 0, (4.5) holds whenever tk ≤ t , wheret = 2
L(2σK+K+1) .
(b) We have tk ≥ mint, βt for all k.
(c) dk → 0 and every cluster point of xk is a stationarypoint.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 29 / 32
4. IUG method for Karcher mean
Conclusions
In this paper we consider IUG method for the Karther meanmotivated by the observations that implementable algorithms offinding the Karcher mean on general settings beyond matrix case arenot as many as expected, and the objective function of the consideredminimization problem is the sum of many smooth functions.
We have shown the global convergence of the proposed methodsexploiting the Lipschitz continuity of the gradient of the objectivefunction.
Even though our method is faster than SD, we need to furtheraccelerate the proposed method so that it becomes more attractive.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 30 / 32
4. IUG method for Karcher mean
Conclusions
In this paper we consider IUG method for the Karther meanmotivated by the observations that implementable algorithms offinding the Karcher mean on general settings beyond matrix case arenot as many as expected, and the objective function of the consideredminimization problem is the sum of many smooth functions.
We have shown the global convergence of the proposed methodsexploiting the Lipschitz continuity of the gradient of the objectivefunction.
Even though our method is faster than SD, we need to furtheraccelerate the proposed method so that it becomes more attractive.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 30 / 32
4. IUG method for Karcher mean
Conclusions
In this paper we consider IUG method for the Karther meanmotivated by the observations that implementable algorithms offinding the Karcher mean on general settings beyond matrix case arenot as many as expected, and the objective function of the consideredminimization problem is the sum of many smooth functions.
We have shown the global convergence of the proposed methodsexploiting the Lipschitz continuity of the gradient of the objectivefunction.
Even though our method is faster than SD, we need to furtheraccelerate the proposed method so that it becomes more attractive.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 30 / 32
4. IUG method for Karcher mean
Conclusions
In this paper we consider IUG method for the Karther meanmotivated by the observations that implementable algorithms offinding the Karcher mean on general settings beyond matrix case arenot as many as expected, and the objective function of the consideredminimization problem is the sum of many smooth functions.
We have shown the global convergence of the proposed methodsexploiting the Lipschitz continuity of the gradient of the objectivefunction.
Even though our method is faster than SD, we need to furtheraccelerate the proposed method so that it becomes more attractive.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 30 / 32
4. IUG method for Karcher mean
Two directions may be taken into account.
First, a tight bound for Lipschitz constant or a scheme is necessary foradjusting the better stepsize without evaluating the objective value.
Second, a fully Riemannian version of the proposed incrementalgradient method can be a better alternative.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 31 / 32
4. IUG method for Karcher mean
Two directions may be taken into account.
First, a tight bound for Lipschitz constant or a scheme is necessary foradjusting the better stepsize without evaluating the objective value.
Second, a fully Riemannian version of the proposed incrementalgradient method can be a better alternative.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 31 / 32
4. IUG method for Karcher mean
Two directions may be taken into account.
First, a tight bound for Lipschitz constant or a scheme is necessary foradjusting the better stepsize without evaluating the objective value.
Second, a fully Riemannian version of the proposed incrementalgradient method can be a better alternative.
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 31 / 32
References
[1] Karcher, H.: Riemannian center of mass and mollifier smoothing. Comm.Pure Appl. Math. 30, 509–541 (1977)
[2] Afsari, B., Tron, R., Vidal, R.: On the convergence of gradient descent forfinding the Riemannian center of mass. SIAM J. Control Optim. 51, 2230–2260(2013)
[3] Tseng, P., Yun, S.: Incrementally updated gradient methods for constrainedand regularized optimization. J. Optim. Theory Appl. 160, 832–853 (2014)
[4] Kum, S., Lee, H., Lim, Y.: No dice theorem on symmetric cones. TaiwaneseJ. Math. 17, 1967–1982 (2013)
[5] Holbrook, J.: No dice: a determinstic approach to the Cartan centroid. J.Ramanujan Math. Soc. 27, 509-521 (2012)
Sangho Kum and Sangwoon Yun (CBNU) Incremental gradient method for Karcher mean July 5, 2016 32 / 32