Strong convexity of sandwiched entropies and related optimization problems

被引:18
作者
Bhatia, Rajendra [1 ]
Jain, Tanvi [2 ]
Lim, Yongdo [3 ]
机构
[1] Ashoka Univ, Sonepat 131029, Haryana, India
[2] Indian Stat Inst, New Delhi 110016, India
[3] Sungkyunkwan Univ, Dept Math, Suwon 440746, South Korea
基金
新加坡国家研究基金会;
关键词
Positive definite matrix; multimarginal optimal transport; fidelity; sand-wiched quasi-relative entropy; strong convexity; gradient projection algorithm; TRANSITION-PROBABILITY; DISTANCE; GEOMETRY;
D O I
10.1142/S0129055X18500149
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
We present several theorems on strict and strong convexity, and higher order differential formulae for sandwiched quasi-relative entropy (a parametrized version of the classical fidelity). These are crucial for establishing global linear convergence of the gradient projection algorithm for optimization problems for these functions. The case of the classical fidelity is of special interest for the multimarginal optimal transport problem (the n-coupling problem) for Gaussian measures.
引用
收藏
页数:18
相关论文
共 38 条
[1]   BARYCENTERS IN THE WASSERSTEIN SPACE [J].
Agueh, Martial ;
Carlier, Guillaume .
SIAM JOURNAL ON MATHEMATICAL ANALYSIS, 2011, 43 (02) :904-924
[2]   A NOTE ON THE TRANSITION-PROBABILITY OVER C-STAR-ALGEBRAS [J].
ALBERTI, PM .
LETTERS IN MATHEMATICAL PHYSICS, 1983, 7 (01) :25-32
[3]  
Ando T, 1995, OPER THEOR, V75, P33
[4]   Geometrical significance of the Lowner-Heinz inequality [J].
Andruchow, E ;
Corach, G ;
Stojanoff, D .
PROCEEDINGS OF THE AMERICAN MATHEMATICAL SOCIETY, 2000, 128 (04) :1031-1037
[5]   Convex Optimization: Algorithms and Complexity [J].
不详 .
FOUNDATIONS AND TRENDS IN MACHINE LEARNING, 2015, 8 (3-4) :232-+
[6]  
[Anonymous], 2017, Geometry of Quantum States: An Introduction to Quantum Entanglement, DOI DOI 10.1017/9781139207010
[7]  
[Anonymous], 2013, Matrix Analysis
[8]  
[Anonymous], 1963, P AM MATH SOC
[9]  
[Anonymous], REP MATH PHYS
[10]  
[Anonymous], GRADIENT PROJECTION