English
Related papers

Related papers: Geometry and convergence of natural policy gradien…

200 papers

In proper, geodesic Gromov hyperbolic spaces, we investigate discrete-time gradient flows via the proximal point algorithm for unbounded Lipschitz convex functions. Assuming that the target convex function has negative asymptotic slope…

Optimization and Control · Mathematics 2025-10-24 Shin-ichi Ohta

We analyze the convergence rate of gradient flows on objective functions induced by Dropout and Dropconnect, when applying them to shallow linear Neural Networks (NNs) - which can also be viewed as doing matrix factorization using a…

Machine Learning · Computer Science 2020-12-04 Albert Senen-Cerda , Jaron Sanders

Policy gradient methods are a powerful family of reinforcement learning algorithms for continuous control that optimize a policy directly. However, standard first-order methods often converge slowly. Second-order methods can accelerate…

Systems and Control · Electrical Eng. & Systems 2025-11-05 Amirreza Valaei , Arash Bahari Kordabad , Sadegh Soudjani

Contraction analysis establishes exponential incremental convergence of a nonlinear system by solving a linear matrix inequality for a contraction metric, and has become a standard resource for solving problems in nonlinear control and…

Dynamical Systems · Mathematics 2026-03-03 Winfried Lohmiller , Jean-Jacques Slotine

Constrained Reinforcement Learning (CRL) addresses sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints. In this setting, policy-based…

Machine Learning · Computer Science 2025-06-09 Alessandro Montenegro , Leonardo Cesani , Marco Mussi , Matteo Papini , Alberto Maria Metelli

Motivated by energy based analyses for descent methods in the Euclidean setting, we investigate a generalisation of such analyses for descent methods over Riemannian manifolds. In doing so, we find that it is possible to derive…

Optimization and Control · Mathematics 2022-12-13 Vishwak Srinivasan , Ashia Wilson

We study high-probability (HP) convergence guarantees in decentralized stochastic optimization, where multiple agents collaborate to jointly train a model over a network. Existing HP results in decentralized settings almost exclusively…

Machine Learning · Computer Science 2026-05-04 Aleksandar Armacki , Haoyuan Cai , Ali H. Sayed

Recently, policy optimization for control purposes has received renewed attention due to the increasing interest in reinforcement learning. In this paper, we investigate the global convergence of gradient-based policy optimization methods…

Optimization and Control · Mathematics 2020-11-25 Joao Paulo Jansch-Porto , Bin Hu , Geir Dullerud

We present two Policy Gradient-based algorithms with general parametrization in the context of infinite-horizon average reward Markov Decision Process (MDP). The first one employs Implicit Gradient Transport for variance reduction, ensuring…

Machine Learning · Computer Science 2025-05-13 Swetha Ganesh , Washim Uddin Mondal , Vaneet Aggarwal

This paper considers the analysis of continuous time gradient-based optimization algorithms through the lens of nonlinear contraction theory. It demonstrates that in the case of a time-invariant objective, most elementary results on…

Optimization and Control · Mathematics 2022-12-23 Patrick M. Wensing , Jean-Jacques E. Slotine

While momentum-based optimization algorithms are commonly used in the notoriously non-convex optimization problems of deep learning, their analysis has historically been restricted to the convex and strongly convex setting. In this article,…

Optimization and Control · Mathematics 2025-05-14 Kanan Gupta , Stephan Wojtowytsch

We consider variants of a recently-developed Newton-CG algorithm for nonconvex problems \citep{royer2018newton} in which inexact estimates of the gradient and the Hessian information are used for various steps. Under certain conditions on…

Optimization and Control · Mathematics 2022-04-12 Zhewei Yao , Peng Xu , Fred Roosta , Stephen J. Wright , Michael W. Mahoney

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from…

Machine Learning · Computer Science 2026-01-27 Shihab Ahmed , El Houcine Bergou , Aritra Dutta , Yue Wang

This paper proposes and develops new linesearch methods with inexact gradient information for finding stationary points of nonconvex continuously differentiable functions on finite-dimensional spaces. Some abstract convergence results for a…

Optimization and Control · Mathematics 2023-01-03 Pham Duy Khanh , Boris S. Mordukhovich , Dat Ba Tran

In modern robotics, effectively computing optimal control policies under dynamically varying environments poses substantial challenges to the off-the-shelf parametric policy gradient methods, such as the Deep Deterministic Policy Gradient…

Robotics · Computer Science 2022-03-29 Apan Dastider , Mingjie Lin

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

We study Concave Constrained Markov Decision Processes (Concave CMDPs) where both the objective and constraints are defined as concave functions of the state-action occupancy measure. We propose the Variance-Reduced Primal-Dual Policy…

Machine Learning · Computer Science 2024-05-28 Donghao Ying , Mengzi Amy Guo , Hyunin Lee , Yuhao Ding , Javad Lavaei , Zuo-Jun Max Shen

Stochastic gradient descent is one of the most successful approaches for solving large-scale problems, especially in machine learning and statistics. At each iteration, it employs an unbiased estimator of the full gradient computed from one…

Numerical Analysis · Mathematics 2018-12-05 Bangti Jin , Xiliang Lu

In this contribution, we present a full overview of the continuous stochastic gradient (CSG) method, including convergence results, step size rules and algorithmic insights. We consider optimization problems in which the objective function…

Optimization and Control · Mathematics 2023-03-23 Max Grieshammer , Lukas Pflug , Michael Stingl , Andrian Uihlein

We study the convergence rate of Bregman gradient methods for convex optimization in the space of measures on a $d$-dimensional manifold. Under basic regularity assumptions, we show that the suboptimality gap at iteration $k$ is in…

Optimization and Control · Mathematics 2023-03-15 Lénaïc Chizat
‹ Prev 1 8 9 10 Next ›