English
Related papers

Related papers: Convergence of Policy Mirror Descent Beyond Compat…

200 papers

Policy gradient methods have been frequently applied to problems in control and reinforcement learning with great success, yet existing convergence analysis still relies on non-intuitive, impractical and often opaque conditions. In…

Machine Learning · Computer Science 2022-04-08 Matthew S. Zhang , Murat A. Erdogdu , Animesh Garg

While there is an extensive body of research analyzing policy gradient methods for discounted cumulative-reward MDPs, prior work on policy gradient methods for average-reward MDPs has been limited, with most existing results restricted to…

Optimization and Control · Mathematics 2026-02-23 Jongmin Lee , Ernest K. Ryu

Smoothness is crucial for attaining fast rates in first-order optimization. However, many optimization problems in modern machine learning involve non-smooth objectives. Recent studies relax the smoothness assumption by allowing the…

Optimization and Control · Mathematics 2026-02-11 Dingzhi Yu , Wei Jiang , Hongyi Tao , Yuanyu Wan , Lijun Zhang

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

We focus on parameterized policy search for reinforcement learning over continuous action spaces. Typically, one assumes the score function associated with a policy is bounded, which fails to hold even for Gaussian policies. To properly…

Machine Learning · Computer Science 2022-02-01 Amrit Singh Bedi , Souradip Chakraborty , Anjaly Parayil , Brian Sadler , Pratap Tokekar , Alec Koppel

Attention mechanisms have revolutionized several domains of artificial intelligence, such as natural language processing and computer vision, by enabling models to selectively focus on relevant parts of the input data. While recent work has…

Machine Learning · Computer Science 2026-02-03 Addison Kristanto Julistiono , Davoud Ataee Tarzanagh , Navid Azizan

We consider centralized and distributed mirror descent algorithms over a finite-dimensional Hilbert space, and prove that the problem variables converge to an optimizer of a possibly nonsmooth function when the step sizes are square…

Optimization and Control · Mathematics 2018-05-07 Thinh T. Doan , Subhonmesh Bose , D. Hoa Nguyen , Carolyn L. Beck

This paper seeks to address how to solve non-smooth convex and strongly convex optimization problems with functional constraints. The introduced Mirror Descent (MD) method with adaptive stepsizes is shown to have a better convergence rate…

Optimization and Control · Mathematics 2017-05-08 Anastasia Bayandina

Constrained competitive optimization involves multiple agents trying to minimize conflicting objectives, subject to constraints. This is a highly expressive modeling language that subsumes most of modern machine learning. In this work we…

Optimization and Control · Mathematics 2020-06-19 Florian Schäfer , Anima Anandkumar , Houman Owhadi

We study an explicit mirror-descent method for finite-horizon deterministic optimal control problems. The method is motivated by Pontryagin's maximum principle: at each iteration, one solves the state and adjoint equations and updates the…

Optimization and Control · Mathematics 2026-05-05 Ye Feng , Jianfeng Lu

Low-rank and nonsmooth matrix optimization problems capture many fundamental tasks in statistics and machine learning. While significant progress has been made in recent years in developing efficient methods for \textit{smooth} low-rank…

Optimization and Control · Mathematics 2025-04-10 Dan Garber , Atara Kaplan

We study stochastic convex optimization under infinite noise variance. Specifically, when the stochastic gradient is unbiased and has uniformly bounded $(1+\kappa)$-th moment, for some $\kappa \in (0,1]$, we quantify the convergence rate of…

Machine Learning · Statistics 2022-02-24 Nuri Mert Vural , Lu Yu , Krishnakumar Balasubramanian , Stanislav Volgushev , Murat A. Erdogdu

Mirror Descent is a popular algorithm, that extends Gradients Descent (GD) beyond the Euclidean geometry. One of its benefits is to enable strong convergence guarantees through smooth-like analyses, even for objectives with exploding or…

Optimization and Control · Mathematics 2024-04-19 Hadrien Hendrikx

Policy gradient (PG) methods are a widely used reinforcement learning methodology in many applications such as video games, autonomous driving, and robotics. In spite of its empirical success, a rigorous understanding of the global…

Optimization and Control · Mathematics 2020-06-30 Kaiqing Zhang , Alec Koppel , Hao Zhu , Tamer Başar

The paper is devoted to new modifications of recently proposed adaptive methods of Mirror Descent for convex minimization problems in the case of several convex functional constraints. Methods for problems of two classes are considered. The…

Optimization and Control · Mathematics 2018-05-29 Fedor S. Stonyakin , Mohammad S. Alkousa , Alexey N. Stepanov , Maxim A. Barinov

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

Finding optimal policies for Partially Observable Markov Decision Processes (POMDPs) is challenging due to their uncountable state spaces when transformed into fully observable Markov Decision Processes (MDPs) using belief states.…

Optimization and Control · Mathematics 2024-09-09 Yunus Emre Demirci , Ali Devran Kara , Serdar Yüksel

Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms in contemporary reinforcement learning. This class of methods is often applied in conjunction with entropy regularization -- an algorithmic…

Machine Learning · Statistics 2022-09-13 Shicong Cen , Chen Cheng , Yuxin Chen , Yuting Wei , Yuejie Chi

We revisit the finite time analysis of policy gradient methods in the one of the simplest settings: finite state and action MDPs with a policy class consisting of all stochastic policies and with exact gradient evaluations. There has been…

Machine Learning · Computer Science 2021-12-14 Jalaj Bhandari , Daniel Russo

The majorization-minimization (MM) principle is an extremely general framework for deriving optimization algorithms. It includes the expectation-maximization (EM) algorithm, proximal gradient algorithm, concave-convex procedure, quadratic…

Optimization and Control · Mathematics 2021-06-08 Kenneth Lange , Joong-Ho Won , Alfonso Landeros , Hua Zhou