English
Related papers

Related papers: Linear Convergence for Natural Policy Gradient wit…

200 papers

We consider the problem of designing sample efficient learning algorithms for infinite horizon discounted reward Markov Decision Process. Specifically, we propose the Accelerated Natural Policy Gradient (ANPG) algorithm that utilizes an…

Machine Learning · Computer Science 2024-02-06 Washim Uddin Mondal , Vaneet Aggarwal

Natural gradients have long been studied in deep reinforcement learning due to their fast convergence properties and covariant weight updates. However, computing natural gradients requires inversion of the Fisher Information Matrix (FIM) at…

Machine Learning · Computer Science 2026-02-12 Yingxiao Huo , Satya Prakash Dash , Radu Stoican , Samuel Kaski , Mingfei Sun

Knowledge gradient is a design principle for developing Bayesian sequential sampling policies to solve optimization problems. In this paper we consider the ranking and selection problem in the presence of covariates, where the best…

Statistics Theory · Mathematics 2022-01-17 Liang Ding , L. Jeff Hong , Haihui Shen , Xiaowei Zhang

Learning-to-optimize leverages machine learning to accelerate optimization algorithms. While empirical results show tremendous improvements compared to classical optimization algorithms, theoretical guarantees are mostly lacking, such that…

Machine Learning · Computer Science 2025-06-02 Michael Sucker , Peter Ochs

While policy optimization algorithms have played an important role in recent empirical success of Reinforcement Learning (RL), the existing theoretical understanding of policy optimization remains rather limited -- they are either…

Machine Learning · Computer Science 2023-12-05 Qinghua Liu , Gellért Weisz , András György , Chi Jin , Csaba Szepesvári

Our goal is to compute a policy that guarantees improved return over a baseline policy even when the available MDP model is inaccurate. The inaccurate model may be constructed, for example, by system identification techniques when the true…

Optimization and Control · Mathematics 2015-06-17 Yinlam Chow , Marek Petrik , Mohammad Ghavamzadeh

Motivated by policy gradient methods in the context of reinforcement learning, we identify a large deviation rate function for the iterates generated by stochastic gradient descent for possibly non-convex objectives satisfying a…

Optimization and Control · Mathematics 2024-06-04 Wouter Jongeneel , Daniel Kuhn , Mengmeng Li

We study deterministic and stochastic primal-dual sub-gradient algorithms for distributed optimization of a separable objective function with global inequality constraints. In both algorithms, the norm of the Lagrangian multipliers are…

Optimization and Control · Mathematics 2017-06-20 Masoud Badiei Khuzani , Na Li

Policy gradient (PG) methods are the backbone of many reinforcement learning algorithms due to their good performance in policy optimization problems. As a gradient-based approach, PG methods typically rely on knowledge of the system…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Bowen Song , Andrea Iannelli

We consider the problem of estimating the factors of a rank-$1$ matrix with i.i.d. Gaussian, rank-$1$ measurements that are nonlinearly transformed and corrupted by noise. Considering two prototypical choices for the nonlinearity, we study…

Optimization and Control · Mathematics 2024-10-02 Kabir Aladin Chandrasekher , Mengqi Lou , Ashwin Pananjady

For deterministic optimization, line-search methods augment algorithms by providing stability and improved efficiency. We adapt a classical backtracking Armijo line-search to the stochastic optimization setting. While traditional…

Optimization and Control · Mathematics 2018-07-24 Courtney Paquette , Katya Scheinberg

Recently there has been renewed interests in derivative free approaches to stochastic optimization. In this paper, we examine the rates of convergence for the Kiefer-Wolfowitz algorithm and the mirror descent algorithm, under various…

Optimization and Control · Mathematics 2016-10-31 Liyi Dai

Designing a multi-layer optical system with designated optical characteristics is an inverse design problem in which the resulting design is determined by several discrete and continuous parameters. In particular, we consider three design…

Machine Learning · Computer Science 2021-11-17 Heribert Wankerl , Maike L. Stern , Ali Mahdavi , Christoph Eichler , Elmar W. Lang

We consider a broad class of dynamic programming (DP) problems that involve a partially linear structure and some positivity properties in their system equation and cost function. We address deterministic and stochastic problems, possibly…

Optimization and Control · Mathematics 2026-04-21 Yuchao Li , Dimitri Bertsekas

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

With the rise of the digital economy and an explosion of available information about consumers, effective personalization of goods and services has become a core business focus for companies to improve revenues and maintain a competitive…

Machine Learning · Computer Science 2022-11-04 Zhaonan Qu , Isabella Qian , Zhengyuan Zhou

Gradient-based solvers risk convergence to local optima, leading to incorrect researcher inference. Heuristic-based algorithms are able to ``break free" of these local optima to eventually converge to the true global optimum. However, given…

Econometrics · Economics 2024-01-17 Zachary Porreca

A novel Policy Gradient (PG) algorithm, called $\textit{Matryoshka Policy Gradient}$ (MPG), is introduced and studied, in the context of fixed-horizon max-entropy reinforcement learning, where an agent aims at maximizing entropy bonuses…

Machine Learning · Computer Science 2024-10-10 François Ged , Maria Han Veiga

Recent policy optimization approaches have achieved substantial empirical success by constructing surrogate optimization objectives. The Approximate Policy Iteration objective (Schulman et al., 2015a; Kakade and Langford, 2002) has become a…

Machine Learning · Computer Science 2019-10-31 Marcin B. Tomczak , Sergio Valcarcel Macua , Enrique Munoz de Cote , Peter Vrancx

Most existing methodologies of estimating low-rank matrices rely on Burer-Monteiro factorization, but these approaches can suffer from slow convergence, especially when dealing with solutions characterized by a large condition number,…

Optimization and Control · Mathematics 2024-03-06 Teng Zhang , Xing Fan