English
Related papers

Related papers: SBEED: Convergent Reinforcement Learning with Nonl…

200 papers

We develop and analyze stochastic approximation algorithms for solving nested compositional bi-level optimization problems. These problems involve a nested composition of $T$ potentially non-convex smooth functions in the upper-level, and a…

Optimization and Control · Mathematics 2023-07-12 Xuxing Chen , Krishnakumar Balasubramanian , Saeed Ghadimi

Distributional reinforcement learning improves performance by capturing environmental stochasticity, but a comprehensive theoretical understanding of its effectiveness remains elusive. In addition, the intractable element of the infinite…

Machine Learning · Computer Science 2025-05-14 Taehyun Cho , Seungyub Han , Seokhun Ju , Dohyeong Kim , Kyungjae Lee , Jungwoo Lee

We introduce a new method for solving nonlinear continuous optimization problems with chance constraints. Our method is based on a reformulation of the probabilistic constraint as a quantile function. The quantile function is approximated…

Optimization and Control · Mathematics 2020-03-17 Alejandra Peña-Ordieres , James R. Luedtke , Andreas Wächter

We study reinforcement learning for partially observed Markov decision processes (POMDPs) with infinite observation and state spaces, which remains less investigated theoretically. To this end, we make the first attempt at bridging partial…

Machine Learning · Computer Science 2024-04-02 Qi Cai , Zhuoran Yang , Zhaoran Wang

We study unconstrained optimization problems with nonsmooth and convex objective function in the form of a mathematical expectation. The proposed method approximates the expected objective function with a sample average function using…

Optimization and Control · Mathematics 2022-11-03 Natasa Krejic , Natasa Krklec Jerinkic , Tijana Ostojic

We consider the problem of reinforcement learning using function approximation, where the approximating basis can change dynamically while interacting with the environment. A motivation for such an approach is maximizing the value function…

Machine Learning · Computer Science 2010-05-04 Dotan Di Castro , Shie Mannor

The training of deep neural networks predominantly relies on a combination of gradient-based optimisation and back-propagation for the computation of the gradient. While incredibly successful, this approach faces challenges such as…

Machine Learning · Computer Science 2026-02-09 Xiaoyu Wang , Alexandra Valavanis , Azhir Mahmood , Andreas Mang , Martin Benning , Audrey Repetti

Existing value function approximation methods have been successfully used in many applications, but they often lack useful a priori error bounds. We propose a new approximate bilinear programming formulation of value function approximation,…

Artificial Intelligence · Computer Science 2010-06-15 Marek Petrik , Shlomo Zilberstein

Nonconvex-nonconcave minimax optimization has gained widespread interest over the last decade. However, most existing works focus on variants of gradient descent-ascent (GDA) algorithms, which are only applicable to smooth nonconvex-concave…

Optimization and Control · Mathematics 2025-01-17 Jiajin Li , Linglingzhi Zhu , Anthony Man-Cho So

The convergence of many reinforcement learning (RL) algorithms with linear function approximation has been investigated extensively but most proofs assume that these methods converge to a unique solution. In this paper, we provide a…

Machine Learning · Computer Science 2019-05-29 Marcus Hutter , Samuel Yang-Zhao , Sultan J. Majeed

Modern statistical applications often involve minimizing an objective function that may be nonsmooth and/or nonconvex. This paper focuses on a broad Bregman-surrogate algorithm framework including the local linear approximation, mirror…

Optimization and Control · Mathematics 2021-12-20 Yiyuan She , Zhifeng Wang , Jiuwu Jin

Reinforcement Learning (RL) algorithms allow artificial agents to improve their action selections so as to increase rewarding experiences in their environments. Deep Reinforcement Learning algorithms require solving a nonconvex and…

Machine Learning · Computer Science 2019-04-18 Jacob Rafati , Roummel F. Marcia

We provide improved convergence rates for various \emph{non-smooth} optimization problems via higher-order accelerated methods. In the case of $\ell_\infty$ regression, we achieves an $O(\epsilon^{-4/5})$ iteration complexity, breaking the…

Optimization and Control · Mathematics 2019-06-05 Brian Bullins , Richard Peng

We introduce Bella, a locally superlinearly convergent Bregman forward backward splitting method for minimizing the sum of two nonconvex functions, one of which satisfying a relative smoothness condition and the other one possibly…

Optimization and Control · Mathematics 2024-04-17 Masoud Ahookhosh , Andreas Themelis , Panagiotis Patrinos

This paper develops an inverse reinforcement learning algorithm aimed at recovering a reward function from the observed actions of an agent. We introduce a strategy to flexibly handle different types of actions with two approximations of…

Machine Learning · Computer Science 2017-07-26 Kun Li , Yanan Sui , Joel W. Burdick

Inverse problems are in many cases solved with optimization techniques. When the underlying model is linear, first-order gradient methods are usually sufficient. With nonlinear models, due to nonconvexity, one must often resort to…

Numerical Analysis · Mathematics 2023-05-15 Arttu Arjas , Mikko J. Sillanpää , Andreas Hauptmann

We provide a lower bound showing that the $O(1/k)$ convergence rate of the NoLips method (a.k.a. Bregman Gradient) is optimal for the class of functions satisfying the $h$-smoothness assumption. This assumption, also known as relative…

Optimization and Control · Mathematics 2021-02-18 Radu-Alexandru Dragomir , Adrien Taylor , Alexandre d'Aspremont , Jérôme Bolte

We present a new algorithm for solving optimization problems with objective functions that are the sum of a smooth function and a (potentially) nonsmooth regularization function, and nonlinear equality constraints. The algorithm may be…

Optimization and Control · Mathematics 2024-04-12 Yutong Dai , Xiaoyi Qu , Daniel P. Robinson

Federated learning enables training on a massive number of edge devices. To improve flexibility and scalability, we propose a new asynchronous federated optimization algorithm. We prove that the proposed approach has near-linear convergence…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-12-08 Cong Xie , Sanmi Koyejo , Indranil Gupta

In this paper, we propose a variance-reduced primal-dual algorithm with Bregman distance for solving convex-concave saddle-point problems with finite-sum structure and nonbilinear coupling function. This type of problems typically arises in…

Optimization and Control · Mathematics 2021-06-02 Erfan Yazdandoost Hamedani , Afrooz Jalilzadeh