English
Related papers

Related papers: Global Optimality Guarantees For Policy Gradient M…

200 papers

Markov Decision Processes (MDPs) are a formal framework for modeling and solving sequential decision-making problems. In finite-time horizons such problems are relevant for instance for optimal stopping or specific supply chain problems,…

Optimization and Control · Mathematics 2024-05-07 Sara Klein , Simon Weissmann , Leif Döring

We establish novel generalization bounds for learning algorithms that converge to global minima. We do so by deriving black-box stability results that only depend on the convergence of a learning algorithm and the geometry around the…

Machine Learning · Statistics 2017-10-25 Zachary Charles , Dimitris Papailiopoulos

This paper presents an algorithmic framework for solving unconstrained stochastic optimization problems using only stochastic function evaluations. We employ central finite-difference based gradient estimation methods to approximate the…

Optimization and Control · Mathematics 2025-01-14 Raghu Bollapragada , Cem Karamanli

We consider infinite-horizon discounted Markov decision problems with finite state and action spaces and study the convergence rates of the projected policy gradient method and a general class of policy mirror descent methods, all with…

Optimization and Control · Mathematics 2022-03-08 Lin Xiao

Interpreting gradient methods as fixed-point iterations, we provide a detailed analysis of those methods for minimizing convex objective functions. Due to their conceptual and algorithmic simplicity, gradient methods are widely used in…

Machine Learning · Statistics 2017-08-16 Alexander Jung

The success of deep learning is due, to a large extent, to the remarkable effectiveness of gradient-based optimization methods applied to large neural networks. The purpose of this work is to propose a modern view and a general mathematical…

Machine Learning · Computer Science 2021-05-28 Chaoyue Liu , Libin Zhu , Mikhail Belkin

Stochastic nonconvex optimization problems with nonlinear constraints have a broad range of applications in intelligent transportation, cyber-security, and smart grids. In this paper, first, we propose an inexact-proximal accelerated…

Optimization and Control · Mathematics 2021-07-08 Morteza Boroun , Afrooz Jalilzadeh

The {\L}ojasiewicz inequality characterizes objective-value convergence along gradient flows and, in special cases, yields exponential decay of the cost. However, such results do not directly give rates of convergence in the state. In this…

Optimization and Control · Mathematics 2026-03-30 Andreas Oliveira , Arthur C. B. de Oliveira , Mario Sznaier , Eduardo Sontag

In smooth strongly convex optimization, knowledge of the strong convexity parameter is critical for obtaining simple methods with accelerated rates. In this work, we study a class of methods, based on Polyak steps, where this knowledge is…

Optimization and Control · Mathematics 2020-07-06 Mathieu Barré , Adrien Taylor , Alexandre d'Aspremont

Gradient-based methods have been widely used for system design and optimization in diverse application domains. Recently, there has been a renewed interest in studying theoretical properties of these methods in the context of control and…

Optimization and Control · Mathematics 2022-10-11 Bin Hu , Kaiqing Zhang , Na Li , Mehran Mesbahi , Maryam Fazel , Tamer Başar

Gradient-based methods successfully train highly overparameterized models in practice, even though the associated optimization problems are markedly nonconvex. Understanding the mechanisms that make such methods effective has become a…

Machine Learning · Computer Science 2026-01-21 Hippolyte Labarrière , Cesare Molinari , Lorenzo Rosasco , Cristian Vega , Silvia Villa

The policy gradient theorem describes the gradient of the expected discounted return with respect to an agent's policy parameters. However, most policy gradient methods drop the discount factor from the state distribution and therefore do…

Machine Learning · Computer Science 2020-03-02 Chris Nota , Philip S. Thomas

In this work, we consider constrained stochastic optimization problems under hidden convexity, i.e., those that admit a convex reformulation via non-linear (but invertible) map $c(\cdot)$. A number of non-convex problems ranging from…

Optimization and Control · Mathematics 2024-11-12 Ilyas Fatkhullin , Niao He , Yifan Hu

Majorization-minimization algorithms consist of successively minimizing a sequence of upper bounds of the objective function so that along the iterations the objective function decreases. Such a simple principle allows to solve a large…

Optimization and Control · Mathematics 2025-03-04 Ion Necoara , Daniela Lupu

This paper studies a stochastic algorithm for linearly constrained nonconvex optimization, where the objective function is smooth but only unbiased stochastic gradients with bounded variance are available. We propose a momentum-based…

Optimization and Control · Mathematics 2026-04-16 Chenyang Qiu , Mihitha Maithripala , Zongli Lin

This paper investigates a category of constrained fractional optimization problems that emerge in various practical applications. The objective function for this category is characterized by the ratio of a numerator and denominator, both…

Optimization and Control · Mathematics 2026-05-28 Yizun Lin , Jian-Feng Cai , Zhao-Rong Lai , Cheng Li

This paper addresses the study of derivative-free smooth optimization problems, where the gradient information on the objective function is unavailable. Two novel general derivative-free methods are proposed and developed for minimizing…

Optimization and Control · Mathematics 2023-11-29 Pham Duy Khanh , Boris S. Mordukhovich , Dat Ba Tran

We focus on the optimization problem with smooth, possibly nonconvex objectives and a convex constraint set for which the Euclidean projection operation is practically available. Focusing on this setting, we carry out a general convergence…

Optimization and Control · Mathematics 2026-04-23 Matteo Lapucci , Giampaolo Liuzzi , Stefano Lucidi , Marco Sciandrone , Diego Scuppa

The study of first-order optimization is sensitive to the assumptions made on the objective functions. These assumptions induce complexity classes which play a key role in worst-case analysis, including the fundamental concept of algorithm…

Optimization and Control · Mathematics 2024-05-30 Charles Guille-Escuret , Adam Ibrahim , Baptiste Goujaud , Ioannis Mitliagkas

Policy gradient methods are known to be highly sensitive to the choice of policy parameterization. In particular, the widely used softmax parameterization can induce ill-conditioned optimization landscapes and lead to exponentially slow…

Machine Learning · Computer Science 2026-04-02 Safwan Labbi , Daniil Tiapkin , Paul Mangold , Eric Moulines