Conformal mirror descent with logarithmic divergences

DOI10.1007/s41884-022-00089-3arXiv2209.02938MaRDI QIDQ6138802

Ting-Kam Leonard Wong, Amanjit Singh Kainth, Frank Rudzicz

Publication date: 16 January 2024

Published in: Information Geometry (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2209.02938

zbMATH Keywords

logarithmic divergenceconformal Hessian metricconformal mirror descentDirichlet optimal transportHessian gradient flow

Mathematics Subject Classification ID

Calculus of variations and optimal control; optimization (49-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The geometry of relative arbitrage
• Isometric logratio transformations for compositional data analysis
• Information geometry and its applications
• Continuity, curvature, and the general covariance of optimal transportation
• Stability of a 4th-order curvature condition arising in optimal transport theory
• Geometry of minimum contrast
• Gradient systems in view of information geometry
• Logarithmic divergences from optimal transport and Rényi geometry
• Exponentially concave functions and a new information geometry
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Cramér-Rao lower bounds arising from generalized Csiszár divergences
• Projection theorems and estimating equations for power-law models
• Pseudo-Riemannian geometry encodes information geometry in optimal transport
• Multiplicative Schrödinger problem and the Dirichlet transport
• A gradient descent perspective on Sinkhorn
• Logarithmic divergences: geometry and interpretation of curvature
• A Regression Model for Compositional Data Based on the Shifted-Dirichlet Distribution
• On Conformal Divergences and Their Population Minimizers
• Rényi Divergence and Kullback-Leibler Divergence
• Generalised Thermostatistics
• Polar factorization and monotone rearrangement of vector‐valued functions
• A variational perspective on accelerated methods in optimization
• Hessian Riemannian Gradient Flows in Convex Programming
• Information Geometry of U-Boost and Bregman Divergence
• Information Geometry in Portfolio Theory
• Tsallis and Rényi Deformations Linked via a New λ-Duality
• A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices
• Information Geometry
• Minimum Divergence Methods in Statistical Machine Learning
• The Information Geometry of Mirror Descent
• Information geometry
• Logistic regression, AdaBoost and Bregman distances

This page was built for publication: Conformal mirror descent with logarithmic divergences