English
Related papers

Related papers: A Large Deviations Perspective on Policy Gradient …

200 papers

Off-policy learning refers to the problem of learning the value function of a way of behaving, or policy, while following a different policy. Gradient-based off-policy learning algorithms, such as GTD and TDC/GQ, converge even when using…

Artificial Intelligence · Computer Science 2015-12-15 Lucas Lehnert , Doina Precup

We present an adaptive step-size method, which does not include line-search techniques, for solving a wide class of nonconvex multiobjective programming problems on an unbounded constraint set. We also prove convergence of a general…

Optimization and Control · Mathematics 2024-02-12 Nguyen Anh Minh , Le Dung Muu , Tran Ngoc Thang

Dynamic Programming (DP) provides standard algorithms to solve Markov Decision Processes. However, these algorithms generally do not optimize a scalar objective function. In this paper, we draw connections between DP and (constrained)…

Machine Learning · Computer Science 2019-10-30 Nino Vieillard , Olivier Pietquin , Matthieu Geist

Off-policy learning is key to scaling up reinforcement learning as it allows to learn about a target policy from the experience generated by a different behavior policy. Unfortunately, it has been challenging to combine off-policy learning…

Machine Learning · Computer Science 2019-01-04 Ahmed Touati , Pierre-Luc Bacon , Doina Precup , Pascal Vincent

In this paper, we study the convergence rate of the DCA (Difference-of-Convex Algorithm), also known as the convex-concave procedure, with two different termination criteria that are suitable for smooth and nonsmooth decompositions…

Optimization and Control · Mathematics 2023-02-24 Hadi Abbaszadehpeivasti , Etienne de Klerk , Moslem Zamani

This paper studies an intriguing phenomenon related to the good generalization performance of estimators obtained by using large learning rates within gradient descent algorithms. First observed in the deep learning literature, we show that…

Machine Learning · Statistics 2022-06-06 Gaspard Beugnot , Julien Mairal , Alessandro Rudi

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

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

We prove explicit bounds on the exponential rate of convergence for the momentum stochastic gradient descent scheme (MSGD) for arbitrary, fixed hyperparameters (learning rate, friction parameter) and its continuous-in-time counterpart in…

Optimization and Control · Mathematics 2024-11-07 Benjamin Gess , Sebastian Kassing

In this paper, we study a class of bilevel programming problem where the inner objective function is strongly convex. More specifically, under some mile assumptions on the partial derivatives of both inner and outer objective functions, we…

Optimization and Control · Mathematics 2018-02-08 Saeed Ghadimi , Mengdi Wang

We study the convergence of stochastic gradient descent (SGD) for non-convex objective functions. We establish the local convergence with positive probability under the local \L{}ojasiewicz condition introduced by Chatterjee in…

Machine Learning · Computer Science 2024-01-17 Jing An , Jianfeng Lu

We give sufficient conditions for the expected excess and the upper semideviation of recourse functions to be strongly convex. This is done in the setting of two-stage stochastic programs with complete linear recourse and random right-hand…

Optimization and Control · Mathematics 2018-02-20 Matthias Claus , Rüdiger Schultz , Kai Spürkel

We analyze the global and local behavior of gradient-like flows under stochastic errors towards the aim of solving convex optimization problems with noisy gradient input. We first study the unconstrained differentiable convex case, using a…

Optimization and Control · Mathematics 2024-03-12 Rodrigo Maulen-Soto , Jalal Fadili , Hedy Attouch

Stochastic Gradient Descent (SGD) is being used routinely for optimizing non-convex functions. Yet, the standard convergence theory for SGD in the smooth non-convex setting gives a slow sublinear convergence to a stationary point. In this…

Optimization and Control · Mathematics 2021-03-23 Robert M. Gower , Othmane Sebbouh , Nicolas Loizou

We prove novel convergence results for a stochastic proximal gradient algorithm suitable for solving a large class of convex optimization problems, where a convex objective function is given by the sum of a smooth and a possibly non-smooth…

Optimization and Control · Mathematics 2016-08-11 Lorenzo Rosasco , Silvia Villa , Bang Công Vũ

Policy gradient methods are extensively used in reinforcement learning as a way to optimize expected return. In this paper, we explore the evolution of the policy parameters, for a special class of exactly solvable POMDPs, as a…

Machine Learning · Computer Science 2020-11-04 Gavin McCracken , Colin Daniels , Rosie Zhao , Anna Brandenberger , Prakash Panangaden , Doina Precup

We provide performance guarantees for a variant of simulation-based policy iteration for controlling Markov decision processes that involves the use of stochastic approximation algorithms along with state-of-the-art techniques that are…

Machine Learning · Computer Science 2022-10-17 Anna Winnicki , R. Srikant

We investigate periodic points of the Dyck shift from the viewpoint of large deviations. We establish the level-2 Large Deviation Principle with the rate function given in terms of Kolmogorov-Sinai entropies of shift-invariant Borel…

Dynamical Systems · Mathematics 2025-03-19 Hiroki Takahasi

This paper proposes a novel termination criterion, termed the advantage gap function, for finite state and action Markov decision processes (MDP) and reinforcement learning (RL). By incorporating this advantage gap function into the design…

Machine Learning · Computer Science 2026-03-24 Caleb Ju , Guanghui Lan

We propose policy gradient algorithms which learn risk-sensitive policies in a reinforcement learning (RL) framework. Our proposed algorithms maximize the distortion risk measure (DRM) of the cumulative reward in an episodic Markov decision…

Machine Learning · Computer Science 2024-02-06 Nithia Vijayan , Prashanth L. A