Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:1405.7885 · Letters in Mathematical Physics

On the Joint Convexity of the Bregman Divergence of Matrices

József Pitrik, Dániel Virosztek

Published Mar 23, 2015• 23 citations
arXivHTMLPDF
DOI
10.1007/s11005-015-0757-y

Related papers

Maps on Quantum States Preserving Bregman and Jensen Divergences

Dániel Virosztek

arXiv:1601.06529•Letters in Mathematical Physics•Jun 28, 2016•14 citations

Yet another proof of the joint convexity of relative entropy

Mary Beth Ruskai

arXiv:2112.13763•Letters in Mathematical Physics•Aug 1, 2022•4 citations

Extreme points of the convex set of joint probability distributions with fixed marginals

Kalyanapuram Rangachari Parthasarathy

arXiv:math/0702544•Proceedings - Mathematical Sciences•Nov 1, 2007•4 citations

Maximum entropy and sufficiency

Peter Harremoës

The notion of Bregman divergence and sufficiency will be defined on general convex state spaces. It is demonstrated that only spectral sets can have a Bregman divergence that satisfies a sufficiency condition. Positive elements with trace 1 in a Jordan algebra are examples of spectral sets, and the most important example is the set of density matrices with complex entries. It is conjectured that information theoretic considerations lead directly to the notion of Jordan algebra under some regularity conditions.

arXiv:1607.02259•AIP conference proceedings•Jan 1, 2017•6 citations

A characterization theorem for matrix variances

Dénes Petz, Dániel Virosztek

arXiv:1311.3908•Acta Scientiarum Mathematicarum•Dec 1, 2014•6 citations

Classical and Quantum Iterative Optimization Algorithms Based on Matrix Legendre-Bregman Projections

Zhengfeng Ji

We consider Legendre-Bregman projections defined on the Hermitian matrix space and design iterative optimization algorithms based on them. A general duality theorem is established for Bregman divergences on Hermitian matrices, and it plays a crucial role in proving the convergence of the iterative algorithms. We study both exact and approximate Bregman projection algorithms. In the particular case of Kullback-Leibler divergence, our approximate iterative algorithm gives rise to the non-commutative versions of both the generalized iterative scaling (GIS) algorithm for maximum entropy inference and the AdaBoost algorithm in machine learning as special cases. As the Legendre-Bregman projections are simple matrix functions on Hermitian matrices, quantum algorithmic techniques are applicable to achieve potential speedups in each iteration of the algorithm. We discuss several quantum algorithmic design techniques applicable in our setting, including the smooth function evaluation technique, two-phase quantum minimum finding, and NISQ Gibbs state preparation.

arXiv:2209.14185•Sep 28, 2022•3 citations
The notion of Bregman divergence and sufficiency will be defined on general convex state spaces. It is demonstrated that only spectral sets can have a Bregman divergence that satisfies a sufficiency condition. Positive elements with trace 1 in a Jordan algebra are examples of spectral sets, and the most important example is the set of density matrices with complex entries. It is conjectured that information theoretic considerations lead directly to the notion of Jordan algebra under some regularity conditions.
We consider Legendre-Bregman projections defined on the Hermitian matrix space and design iterative optimization algorithms based on them. A general duality theorem is established for Bregman divergences on Hermitian matrices, and it plays a crucial role in proving the convergence of the iterative algorithms. We study both exact and approximate Bregman projection algorithms. In the particular case of Kullback-Leibler divergence, our approximate iterative algorithm gives rise to the non-commutative versions of both the generalized iterative scaling (GIS) algorithm for maximum entropy inference and the AdaBoost algorithm in machine learning as special cases. As the Legendre-Bregman projections are simple matrix functions on Hermitian matrices, quantum algorithmic techniques are applicable to achieve potential speedups in each iteration of the algorithm. We discuss several quantum algorithmic design techniques applicable in our setting, including the smooth function evaluation technique, two-phase quantum minimum finding, and NISQ Gibbs state preparation.