English
Related papers

Related papers: A scaled Bregman theorem with applications

200 papers

We propose efficient Langevin Monte Carlo algorithms for sampling distributions with nonsmooth convex composite potentials, which is the sum of a continuously differentiable function and a possibly nonsmooth function. We devise such…

Machine Learning · Statistics 2022-07-12 Tim Tsz-Kit Lau , Han Liu

Exponential families and mixture families are parametric probability models that can be geometrically studied as smooth statistical manifolds with respect to any statistical divergence like the Kullback-Leibler (KL) divergence or the…

Machine Learning · Computer Science 2018-03-21 Frank Nielsen , Gaëtan Hadjeres

We consider the problem of metric learning subject to a set of constraints on relative-distance comparisons between the data items. Such constraints are meant to reflect side-information that is not expressed directly in the feature vectors…

Machine Learning · Computer Science 2016-12-06 Ehsan Amid , Aristides Gionis , Antti Ukkonen

This paper expands the Cyclic Block Proximal Gradient method for block separable composite minimization by allowing for inexactly computed gradients and proximal maps. The resultant algorithm, the Inexact Cyclic Block Proximal Gradient…

Optimization and Control · Mathematics 2022-01-05 Leandro Maia , David Huckleberry Gutman , Ryan Christopher Hughes

Decentralized stochastic optimization has emerged as a fundamental paradigm for large-scale machine learning. However, practical implementations often rely on biased gradient estimators arising from communication compression or inexact…

Optimization and Control · Mathematics 2026-04-10 Qing Xu , Yiwei Liao , Wenqi Fan , Xingxing You , Songyi Dian

It was observed that hyperlogarithms provide a tool to carry out Feynman integrals. So far, this method has been applied successfully to finite single-scale processes. However, it can be employed in more general situations. We give examples…

High Energy Physics - Theory · Physics 2014-04-01 Erik Panzer

As the number of samples and dimensionality of optimization problems related to statistics an machine learning explode, block coordinate descent algorithms have gained popularity since they reduce the original problem to several smaller…

Machine Learning · Computer Science 2016-06-24 Rémi Flamary , Alain Rakotomamonjy , Gilles Gasso

In this paper, we propose some accelerated methods for solving optimization problems under the condition of relatively smooth and relatively Lipschitz continuous functions with an inexact oracle. We consider the problem of minimizing the…

Optimization and Control · Mathematics 2024-11-27 O. S. Savchuk , M. S. Alkousa , A. S. Shushko , A. A. Vyguzov , F. S. Stonyakin , D. A. Pasechnyuk , A. V. Gasnikov

The linearized Bregman method is a method to calculate sparse solutions to systems of linear equations. We formulate this problem as a split feasibility problem, propose an algorithmic framework based on Bregman projections and prove a…

Optimization and Control · Mathematics 2013-09-11 Dirk A. Lorenz , Frank Schöpfer , Stephan Wenger

In this paper we consider online mirror descent (OMD) algorithms, a class of scalable online learning algorithms exploiting data geometric structures through mirror maps. Necessary and sufficient conditions are presented in terms of the…

Machine Learning · Computer Science 2019-12-16 Yunwen Lei , Ding-Xuan Zhou

In this paper, we explore a specific optimization problem that involves the combination of a differentiable nonconvex function and a nondifferentiable function. The differentiable component lacks a global Lipschitz continuous gradient,…

Optimization and Control · Mathematics 2024-01-05 Qingsong Wang , Zehui Liu , Chunfeng Cui , Deren Han

Motivated by variational models in continuum mechanics, we introduce a novel algorithm to perform nonsmooth and nonconvex minimizations with linear constraints in Euclidean spaces. We show how this algorithm is actually a natural…

Analysis of PDEs · Mathematics 2015-03-20 Marco Artina , Massimo Fornasier , Francesco Solombrino

The alternating direction method with multipliers (ADMM) has been one of most powerful and successful methods for solving various composite problems. The convergence of the conventional ADMM (i.e., 2-block) for convex objective functions…

Optimization and Control · Mathematics 2015-05-13 Fenghui Wang , Wenfei Cao , Zongben Xu

Logarithmic score and information divergence appear in both information theory, statistics, statistical mechanics, and portfolio theory. We demonstrate that all these topics involve some kind of optimization that leads directly to the use…

Statistics Theory · Mathematics 2015-07-28 Peter Harremoës

Bayesian neural networks (BNNs) provide a formalism to quantify and calibrate uncertainty in deep learning. Current inference approaches for BNNs often resort to few-sample estimation for scalability, which can harm predictive performance,…

Machine Learning · Computer Science 2024-02-14 Zhe Zeng , Guy Van den Broeck

We develop a novel stochastic primal dual splitting method with Bregman distances for solving a structured composite problems involving infimal convolutions in non-Euclidean spaces. The sublinear convergence in expectation of the…

Optimization and Control · Mathematics 2021-03-17 Nguyen Van Dung , Băng Công Vũ

We present two stochastic descent algorithms that apply to unconstrained optimization and are particularly efficient when the objective function is slow to evaluate and gradients are not easily obtained, as in some PDE-constrained…

Optimization and Control · Mathematics 2019-04-30 David Kozak , Stephen Becker , Alireza Doostan , Luis Tenorio

In this short note, we give the convergence analysis of the policy in the recent famous policy mirror descent (PMD). We mainly consider the unregularized setting following [11] with generalized Bregman divergence. The difference is that we…

Optimization and Control · Mathematics 2024-06-04 Dachao Lin , Zhihua Zhang

Information divergence that measures the difference between two nonnegative matrices or tensors has found its use in a variety of machine learning problems. Examples are Nonnegative Matrix/Tensor Factorization, Stochastic Neighbor…

Machine Learning · Computer Science 2014-06-06 Onur Dikmen , Zhirong Yang , Erkki Oja

The K-means algorithm is one of the most widely studied clustering algorithms in machine learning. While extensive research has focused on its ability to achieve a globally optimal solution, there still lacks a rigorous analysis of its…

Machine Learning · Computer Science 2025-06-12 Mingyi Li , Michael R. Metel , Akiko Takeda