English
Related papers

Related papers: A gradient descent perspective on Sinkhorn

200 papers

We introduce Kalman Gradient Descent, a stochastic optimization algorithm that uses Kalman filtering to adaptively reduce gradient variance in stochastic gradient descent by filtering the gradient estimates. We present both a theoretical…

Machine Learning · Statistics 2018-10-30 James Vuckovic

We define a new divergence of von Neumann algebras using a variational expression that is similar in nature to Kosaki's formula for the relative entropy. Our divergence satisfies the usual desirable properties, upper bounds the sandwiched…

Quantum Physics · Physics 2021-11-17 Stefan Hollands

Information geometry applies concepts in differential geometry to probability and statistics and is especially useful for parameter estimation in exponential families where parameters are known to lie on a Riemannian manifold. Connections…

Machine Learning · Statistics 2014-05-01 Garvesh Raskutti , Sayan Mukherjee

Stein Variational Gradient Descent (SVGD) is a popular sampling algorithm used in various machine learning tasks. It is well known that SVGD arises from a discretization of the kernelized gradient flow of the Kullback-Leibler divergence…

Machine Learning · Computer Science 2022-11-22 Lukang Sun , Peter Richtárik

A subgradient method is presented for solving general convex optimization problems, the main requirement being that a strictly-feasible point is known. A feasible sequence of iterates is generated, which converges to within user-specified…

Optimization and Control · Mathematics 2016-05-30 James Renegar

The paper presents a new descent algorithm for locally Lipschitz continuous functions $f:X\to\mathbb{R}$. The selection of a descent direction at some iteration point $x$ combines an approximation of the set-valued gradient of $f$ on a…

Numerical Analysis · Mathematics 2019-10-25 Jan Mankau , Friedemann Schuricht

Stochastic variance reduction algorithms have recently become popular for minimizing the average of a large, but finite, number of loss functions. In this paper, we propose a novel Riemannian extension of the Euclidean stochastic variance…

Machine Learning · Computer Science 2017-04-11 Hiroyuki Kasai , Hiroyuki Sato , Bamdev Mishra

Gradient descent methods are fundamental first-order optimization algorithms in both Euclidean spaces and Riemannian manifolds. However, the exact gradient is not readily available in many scenarios. This paper proposes a novel inexact…

Optimization and Control · Mathematics 2024-09-18 Juan Zhou , Kangkang Deng , Hongxia Wang , Zheng Peng

Deep Bregman divergence measures divergence of data points using neural networks which is beyond Euclidean distance and capable of capturing divergence over distributions. In this paper, we propose deep Bregman divergences for contrastive…

Computer Vision and Pattern Recognition · Computer Science 2021-11-24 Mina Rezaei , Farzin Soleymani , Bernd Bischl , Shekoofeh Azizi

Given a non-negative $n \times m$ real matrix $A$, the {\em matrix scaling} problem is to determine if it is possible to scale the rows and columns so that each row and each column sums to a specified target value for it. This problem…

Data Structures and Algorithms · Computer Science 2018-02-19 Deeparnab Chakrabarty , Sanjeev Khanna

The Kullback-Leibler (KL) divergence plays a central role in probabilistic machine learning, where it commonly serves as the canonical loss function. Optimization in such settings is often performed over the probability simplex, where the…

Machine Learning · Computer Science 2025-07-31 Adwait Datar , Nihat Ay

The mirror descent algorithm is known to be effective in situations where it is beneficial to adapt the mirror map to the underlying geometry of the optimization model. However, the effect of mirror maps on the geometry of distributed…

Optimization and Control · Mathematics 2024-03-13 Anastasia Borovykh , Nikolas Kantas , Panos Parpas , Grigorios A. Pavliotis

In this work we generalize the results for the entropy spectra typically derived for black holes in general relativity to a generic horizon within the spherically symmetric (asymptotically flat and non-flat) space-times of more general…

General Relativity and Quantum Cosmology · Physics 2014-02-19 Jozef Skakala , S. Shankaranarayanan

The main purpose of this paper is to propose a variance-based Bregman extragradient algorithm with line search for solving stochastic variational inequalities, which is robust with respect an unknown Lipschitz constant. We prove the almost…

Optimization and Control · Mathematics 2022-08-31 Xian-Jun Long , Yue-Hong He , Nan-Jing Huang

The conditions of relative smoothness and relative strong convexity were recently introduced for the analysis of Bregman gradient methods for convex optimization. We introduce a generalized left-preconditioning method for gradient descent,…

Optimization and Control · Mathematics 2020-12-09 Chris J. Maddison , Daniel Paulin , Yee Whye Teh , Arnaud Doucet

We show that microscopic entropy formula based on Virasoro algebra follows from properties of stationary Killing horizons for Lagrangians with arbitrary dependence on Riemann tensor. The properties used are consequence of regularity of…

High Energy Physics - Theory · Physics 2009-11-10 M. Cvitan , S. Pallua

We formulate gradient-based Markov chain Monte Carlo (MCMC) sampling as optimization on the space of probability measures, with Kullback-Leibler (KL) divergence as the objective functional. We show that an underdamped form of the Langevin…

Machine Learning · Statistics 2019-10-23 Yi-An Ma , Niladri Chatterji , Xiang Cheng , Nicolas Flammarion , Peter Bartlett , Michael I. Jordan

We consider the problem of sampling from a probability distribution $\pi$ which admits a density w.r.t. a dominating measure. It is well known that this can be written as an optimisation problem over the space of probability distributions…

Methodology · Statistics 2026-05-06 Francesca Romana Crucinio

Stochastic variance reduction algorithms have recently become popular for minimizing the average of a large, but finite number of loss functions. The present paper proposes a Riemannian stochastic quasi-Newton algorithm with variance…

Machine Learning · Computer Science 2017-09-19 Hiroyuki Kasai , Hiroyuki Sato , Bamdev Mishra

In this article a unified approach to iterative soft-thresholding algorithms for the solution of linear operator equations in infinite dimensional Hilbert spaces is presented. We formulate the algorithm in the framework of generalized…

Functional Analysis · Mathematics 2010-10-26 Kristian Bredies , Dirk A. Lorenz