中文
相关论文

相关论文: The Information Geometry of Mirror Descent

200 篇论文

We develop a new Riemannian descent algorithm that relies on momentum to improve over existing first-order methods for geodesically convex optimization. In contrast, accelerated convergence rates proved in prior work have only been shown to…

最优化与控制 · 数学 2021-02-16 Foivos Alimisis , Antonio Orvieto , Gary Bécigneul , Aurelien Lucchi

In this paper, we propose and analyse a family of generalised stochastic composite mirror descent algorithms. With adaptive step sizes, the proposed algorithms converge without requiring prior knowledge of the problem. Combined with an…

最优化与控制 · 数学 2022-11-22 Weijia Shao , Fikret Sivrikaya , Sahin Albayrak

Expectation maximization (EM) is the default algorithm for fitting probabilistic models with missing or latent variables, yet we lack a full understanding of its non-asymptotic convergence properties. Previous works show results along the…

机器学习 · 计算机科学 2022-03-01 Frederik Kunstner , Raunak Kumar , Mark Schmidt

In this dissertation, an abstract formalism extending information geometry is introduced. This framework encompasses a broad range of modelling problems, including possible applications in machine learning and in the information theoretical…

数学物理 · 物理学 2015-01-06 Ben Anthonis

This report concerns the problem of dimensionality reduction through information geometric methods on statistical manifolds. While there has been considerable work recently presented regarding dimensionality reduction for the purposes of…

机器学习 · 统计学 2008-09-30 Kevin M. Carter , Raviv Raich , Alfred O. Hero

The logarithmic divergence is an extension of the Bregman divergence motivated by optimal transport and a generalized convex duality, and satisfies many remarkable properties. Using the geometry induced by the logarithmic divergence, we…

最优化与控制 · 数学 2022-09-08 Amanjit Singh Kainth , Ting-Kam Leonard Wong , Frank Rudzicz

We study the problem of finding the global Riemannian center of mass of a set of data points on a Riemannian manifold. Specifically, we investigate the convergence of constant step-size gradient descent algorithms for solving this problem.…

微分几何 · 数学 2012-01-05 Bijan Afsari , Roberto Tron , René Vidal

In this paper, we consider the problem of phase retrieval, which consists of recovering an $n$-dimensional real vector from the magnitude of its $m$ linear measurements. We propose a mirror descent (or Bregman gradient descent) algorithm…

最优化与控制 · 数学 2024-06-21 Jean-Jacques Godeme , Jalal Fadili , Xavier Buet , Myriam Zerrad , Michel Lequime , Claude Amra

We propose an extension of a special form of gradient descent -- in the literature known as linearised Bregman iteration -- to a larger class of non-convex functions. We replace the classical (squared) two norm metric in the gradient…

最优化与控制 · 数学 2021-05-26 Martin Benning , Marta M. Betcke , Matthias J. Ehrhardt , Carola-Bibiane Schönlieb

We examine a wide class of stochastic approximation algorithms for solving (stochastic) nonlinear problems on Riemannian manifolds. Such algorithms arise naturally in the study of Riemannian optimization, game theory and optimal transport,…

最优化与控制 · 数学 2022-12-29 Mohammad Reza Karimi , Ya-Ping Hsieh , Panayotis Mertikopoulos , Andreas Krause

Statistical inference more often than not involves models which are non-linear in the parameters thus leading to non-Gaussian posteriors. Many computational and analytical tools exist that can deal with non-Gaussian distributions, and…

广义相对论与量子宇宙学 · 物理学 2021-01-20 Eileen Giesel , Robert Reischke , Björn Malte Schäfer , Dominic Chia

We propose a new family of subgradient- and gradient-based methods which converges with optimal complexity for convex optimization problems whose feasible region is simple enough. This includes cases where the objective function is…

最优化与控制 · 数学 2016-08-19 Masaru Ito , Mituhiro Fukuda

We present a primal only derivation of Mirror Descent as a "partial" discretization of gradient flow on a Riemannian manifold where the metric tensor is the Hessian of the Mirror Descent potential. We contrast this discretization to Natural…

机器学习 · 计算机科学 2021-07-05 Suriya Gunasekar , Blake Woodworth , Nathan Srebro

Stochastic optimization powers the scalability of modern artificial intelligence, spanning machine learning, deep learning, reinforcement learning, and large language model training. Yet, existing theory remains largely confined to Hilbert…

机器学习 · 计算机科学 2025-09-18 Johnny R. Zhang , Xiaomei Mi , Gaoyuan Du , Qianyi Sun , Shiqi Wang , Jiaxuan Li , Wenhua Zhou

Modern machine learning increasingly leverages the insight that high-dimensional data often lie near low-dimensional, non-linear manifolds, an idea known as the manifold hypothesis. By explicitly modeling the geometric structure of data…

机器学习 · 计算机科学 2026-03-02 Willem Diepeveen , Deanna Needell

This paper introduces the $(\alpha, \Gamma)$-descent, an iterative algorithm which operates on measures and performs $\alpha$-divergence minimisation in a Bayesian framework. This gradient-based procedure extends the commonly-used…

统计理论 · 数学 2021-10-25 Kamélia Daudel , Randal Douc , François Portier

Safety is an essential requirement for reinforcement learning systems. The newly emerging framework of robust constrained Markov decision processes allows learning policies that satisfy long-term constraints while providing guarantees under…

机器学习 · 计算机科学 2025-12-19 David M. Bossens , Atsushi Nitanda

We describe the first gradient methods on Riemannian manifolds to achieve accelerated rates in the non-convex case. Under Lipschitz assumptions on the Riemannian gradient and Hessian of the cost function, these methods find approximate…

最优化与控制 · 数学 2021-11-29 Christopher Criscitiello , Nicolas Boumal

This paper examines a variety of classical optimization problems, including well-known minimization tasks and more general variational inequalities. We consider a stochastic formulation of these problems, and unlike most previous work, we…

最优化与控制 · 数学 2025-11-11 Vladimir Solodkin , Andrew Veprikov , Aleksandr Beznosikov

When dealing with a parametric statistical model, a Riemannian manifold can naturally appear by endowing the parameter space with the Fisher information metric. The geometry induced on the parameters by this metric is then referred to as…