English
Related papers

Related papers: Competitive Mirror Descent

200 papers

Policy Mirror Descent (PMD) is a popular framework in reinforcement learning, serving as a unifying perspective that encompasses numerous algorithms. These algorithms are derived through the selection of a mirror map and enjoy finite-time…

Machine Learning · Statistics 2026-01-07 Carlo Alfano , Sebastian Towers , Silvia Sapora , Chris Lu , Patrick Rebeschini

Line-search methods are commonly used to solve optimization problems. The simplest line search method is steepest descent where one always moves in the direction of the negative gradient. Newton's method on the other hand is a second-order…

Optimization and Control · Mathematics 2025-08-15 Shikhar Saxena , Tejas Bodas , Arti Yardi

In this paper, we analyze the local convergence rate of optimistic mirror descent methods in stochastic variational inequalities, a class of optimization problems with important applications to learning theory and machine learning. Our…

Optimization and Control · Mathematics 2021-07-06 Waïss Azizian , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos

In this paper, we examine the convergence of mirror descent in a class of stochastic optimization problems that are not necessarily convex (or even quasi-convex), and which we call variationally coherent. Since the standard technique of…

Optimization and Control · Mathematics 2018-07-17 Zhengyuan Zhou , Panayotis Mertikopoulos , Nicholas Bambos , Stephen Boyd , Peter Glynn

Online safe reinforcement learning (RL) plays a key role in dynamic environments, with applications in autonomous driving, robotics, and cybersecurity. The objective is to learn optimal policies that maximize rewards while satisfying safety…

Machine Learning · Computer Science 2025-06-03 Jiahui Zhu , Kihyun Yu , Dabeen Lee , Xin Liu , Honghao Wei

Conic programming has well-documented merits in a gamut of signal processing and machine learning tasks. This contribution revisits a recently developed first-order conic descent (CD) solver, and advances it in three aspects: intuition,…

Optimization and Control · Mathematics 2023-08-16 Bingcong Li , Georgios B. Giannakis

Owing to their connection with generative adversarial networks (GANs), saddle-point problems have recently attracted considerable interest in machine learning and beyond. By necessity, most theoretical guarantees revolve around…

Many optimization problems require balancing multiple conflicting objectives. As gradient descent is limited to single-objective optimization, we introduce its direct generalization: Jacobian descent (JD). This algorithm iteratively updates…

Machine Learning · Computer Science 2025-02-04 Pierre Quinton , Valérian Rey

We present the Multilevel Bregman Proximal Gradient Descent (ML BPGD) method, a novel multilevel optimization framework tailored to constrained convex problems with relative Lipschitz smoothness. Our approach extends the classical…

Optimization and Control · Mathematics 2026-05-06 Yara Elshiaty , Stefania Petra

This work addresses decentralized online optimization in non-stationary environments. A network of agents aim to track the minimizer of a global time-varying convex function. The minimizer evolves according to a known dynamics corrupted by…

Optimization and Control · Mathematics 2016-09-12 Shahin Shahrampour , Ali Jadbabaie

We revisit the classical problem of estimating an unknown distribution from its samples by fitting a mixture model that minimizes cross-entropy loss. Framing the task as a stochastic convex optimization problem over the space of $ M…

Machine Learning · Statistics 2026-05-26 Mohammadreza Ahmadypour , Tara Javidi , Farinaz Koushanfar

Value iteration-type methods have been extensively studied for computing a nearly optimal value function in reinforcement learning (RL). Under a generative sampling model, these methods can achieve sharper sample complexity than policy…

Optimization and Control · Mathematics 2026-04-08 Zhichao Jia , Guanghui Lan

In this paper we consider convergence rate problems for stochastic strongly-convex optimization in the non-Euclidean sense with a constraint set over a time-varying multi-agent network. We propose two efficient non-Euclidean stochastic…

Optimization and Control · Mathematics 2018-08-23 Deming Yuan , Yiguang Hong , Daniel W. C. Ho , Guoping Jiang

The mirror descent algorithm (MDA) generalizes gradient descent by using a Bregman divergence to replace squared Euclidean distance. In this paper, we similarly generalize the alternating direction method of multipliers (ADMM) to Bregman…

Optimization and Control · Mathematics 2014-07-09 Huahua Wang , Arindam Banerjee

In this paper, we present a new stochastic algorithm, namely the stochastic block mirror descent (SBMD) method for solving large-scale nonsmooth and stochastic optimization problems. The basic idea of this algorithm is to incorporate the…

Optimization and Control · Mathematics 2013-09-10 Cong D. Dang , Guanghui Lan

We study the implicit bias of generic optimization methods, such as mirror descent, natural gradient descent, and steepest descent with respect to different potentials and norms, when optimizing underdetermined linear regression or…

Machine Learning · Statistics 2020-06-24 Suriya Gunasekar , Jason Lee , Daniel Soudry , Nathan Srebro

We introduce a dynamic sparse training algorithm based on linearized Bregman iterations / mirror descent that exploits the naturally incurred sparsity by alternating between periods of static and dynamic sparsity pattern updates. The key…

Machine Learning · Computer Science 2026-05-19 Yannick Lunk , Sebastian J. Scott , Leon Bungert

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

The paper concerns optimization problems with general equality and inequality constraints and with constraints expressed by a convex set. In order to solve these problems, the general constraints are treated by an exact penalty functions…

Optimization and Control · Mathematics 2026-05-26 Bogdan K. Jastrzębski , Radosław Pytlak

The stochastic mirror descent (SMD) algorithm is a general class of training algorithms, which includes the celebrated stochastic gradient descent (SGD), as a special case. It utilizes a mirror potential to influence the implicit bias of…

Machine Learning · Computer Science 2022-10-28 Taylan Kargin , Fariborz Salehi , Babak Hassibi