Cover Image

A Large Deviations Perspective on Policy Gradient Algorithms

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jongeneel, Wouter, Kuhn, Daniel, Li, Mengmeng
Format:	Preprint
Published:	2023
Subjects:	Optimization and Control Machine Learning 60F10, 90C26
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets
by: Li, Mengmeng, et al.
Published: (2023)

Stochastic Gradient Descent Revisited
by: Louzi, Azar
Published: (2024)

Mean-Field Langevin Diffusions with Density-dependent Temperature
by: Huang, Yu-Jui, et al.
Published: (2025)

The global convergence time of stochastic gradient descent in non-convex landscapes: Sharp estimates via large deviations
by: Azizian, Waïss, et al.
Published: (2025)

What is the long-run distribution of stochastic gradient descent? A large deviations analysis
by: Azizian, Waïss, et al.
Published: (2024)

A Globally Convergent Gradient Method with Momentum
by: Lapucci, Matteo, et al.
Published: (2024)

Projected Gradient Methods with Momentum
by: Lapucci, Matteo, et al.
Published: (2026)

Optimal Learning via Moderate Deviations Theory
by: Ganguly, Arnab, et al.
Published: (2023)

A Semismooth Newton Stochastic Proximal Point Algorithm with Variance Reduction
by: Milzarek, Andre, et al.
Published: (2022)

cuHALLaR: A GPU Accelerated Low-Rank Augmented Lagrangian Method for Large-Scale Semidefinite Programming
by: Aguirre, Jacob M., et al.
Published: (2025)

A Normal Map-Based Proximal Stochastic Gradient Method: Convergence and Identification Properties
by: Qiu, Junwen, et al.
Published: (2023)

Riemannian Gradient Method with Momentum
by: Leggio, Filippo, et al.
Published: (2026)

Global Optimization of Gaussian processes
by: Schweidtmann, Artur M., et al.
Published: (2020)

Gradient Norm Regularization Second-Order Algorithms for Solving Nonconvex-Strongly Concave Minimax Problems
by: Wang, Jun-Lin, et al.
Published: (2024)

Step-Size Stability in Stochastic Optimization: A Theoretical Perspective
by: Schaipp, Fabian, et al.
Published: (2026)

FedSLoP: Memory-Efficient Federated Learning with Low-Rank Gradient Projection
by: He, Yutong, et al.
Published: (2026)

A User Manual for cuHALLaR: A GPU Accelerated Low-Rank Semidefinite Programming Solver
by: Aguirre, Jacob, et al.
Published: (2025)

A Representation Optimization Dichotomy, Lie-Algebraic Policy Optimization
by: KC, Sooraj, et al.
Published: (2026)

Convex Regularization and Convergence of Policy Gradient Flows under Safety Constraints
by: Malo, Pekka, et al.
Published: (2024)

Splitting the Conditional Gradient Algorithm
by: Woodstock, Zev, et al.
Published: (2023)

Mini-Batch Covariance, Diffusion Limits, and Oracle Complexity in Stochastic Gradient Descent: A Sampling-Design Perspective
by: Zantedeschi, Daniel, et al.
Published: (2026)

Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates
by: Rammal, Ahmad, et al.
Published: (2023)

An Algebraically Converging Stochastic Gradient Descent Algorithm for Global Optimization
by: Engquist, Björn, et al.
Published: (2022)

Depth-first directional search for nonconvex optimization
by: Zhang, Yuxuan, et al.
Published: (2024)

Linear Decision Tree Policies for Integer Linear Programs
by: Guyard, Théo, et al.
Published: (2026)

Strong Global Convergence of the Consensus-Based Optimization Algorithm
by: Bonandin, Sabrina, et al.
Published: (2025)

A Fully Parameter-Free Second-Order Algorithm for Convex-Concave Minimax Problems
by: Wang, Junlin, et al.
Published: (2024)

A New Random Reshuffling Method for Nonsmooth Nonconvex Finite-sum Optimization
by: Qiu, Junwen, et al.
Published: (2023)

Constructive approaches to concentration inequalities with independent random variables
by: Moucer, Celine, et al.
Published: (2024)

A Particle Algorithm for Mean-Field Variational Inference
by: Du, Qiang, et al.
Published: (2024)

Constrained Consensus-Based Optimization and Numerical Heuristics for the Few Particle Regime
by: Beddrich, Jonas, et al.
Published: (2024)

Global convergence of gradient descent for phase retrieval
by: Fougereux, Théodore, et al.
Published: (2024)

A low-rank augmented Lagrangian method for large-scale semidefinite programming based on a hybrid convex-nonconvex approach
by: Monteiro, Renato D. C., et al.
Published: (2024)

Large deviations for interacting particle dynamics for finding mixed equilibria in zero-sum games
by: Nilsson, Viktor, et al.
Published: (2022)

Decision-Scaled Scenario Approach for Rare Chance-Constrained Optimization
by: Choi, Jaeseok, et al.
Published: (2026)

Bilevel Learning via Inexact Stochastic Gradient Descent
by: Salehi, Mohammad Sadegh, et al.
Published: (2025)

NS-RGS: Newton-Schulz based Riemannian gradient method for orthogonal group synchronization
by: Peng, Haiyang, et al.
Published: (2026)

SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning
by: Karagulyan, Avetik, et al.
Published: (2024)

Revisiting Frank-Wolfe for Structured Nonconvex Optimization
by: Maskan, Hoomaan, et al.
Published: (2025)

Large Deviation Asymptotics for the Supermarket Model with Growing Choices
by: Budhiraja, Amarjit, et al.
Published: (2025)