English
Related papers

Related papers: Augmented Lagrangian Method for Last-Iterate Conve…

200 papers

In this paper, we focus on the problem of robustifying reinforcement learning (RL) algorithms with respect to model uncertainties. Indeed, in the framework of model-based RL, we propose to merge the theory of constrained Markov decision…

Machine Learning · Computer Science 2020-10-13 Reazul Hasan Russel , Mouhacine Benosman , Jeroen Van Baar

We study the problem of decentralized constrained POMDPs in a team-setting where the multiple non-strategic agents have asymmetric information. Strong duality is established for the setting of infinite-horizon expected total discounted…

Optimization and Control · Mathematics 2023-08-01 Nouman Khan , Vijay Subramanian

Augmented Lagrangian dual augments the classical Lagrangian dual with a non-negative non-linear penalty function of the violation of the relaxed/dualized constraints in order to reduce the duality gap. We investigate the cases in which…

Optimization and Control · Mathematics 2025-01-20 Avinash Bhardwaj , Vishnu Narayanan , Abhishek Pathapati

We consider convex optimization problems with prioritized equality constraints, which may be infeasible. In many applications, such as network optimization and image reconstruction, it is often desirable to compute solutions that satisfy…

Optimization and Control · Mathematics 2026-05-21 Yuya Yamakawa , Shota Yamanaka , Nobuo Yamashita

Approximate linear programming (ALP) is an efficient approach to solving large factored Markov decision processes (MDPs). The main idea of the method is to approximate the optimal value function by a set of basis functions and optimize…

Artificial Intelligence · Computer Science 2012-06-18 Branislav Kveton , Milos Hauskrecht

In this paper we analyze several inexact fast augmented Lagrangian methods for solving linearly constrained convex optimization problems. Mainly, our methods rely on the combination of excessive-gap-like smoothing technique developed in…

Optimization and Control · Mathematics 2015-05-14 Andrei Patrascu , Ion Necoara , Quoc Tran-Dinh

We present a novel augmented Lagrangian (AL) preconditioner for the solution of linear systems arising from finite element discretizations of elliptic interface problems with jump coefficients. The method is based on the Fictitious Domain…

Numerical Analysis · Mathematics 2026-03-16 Michele Benzi , Marco Feder , Luca Heltai , Federica Mugnaioni

Constrained optimization is popularly seen in reinforcement learning for addressing complex control tasks. From the perspective of dynamic system, iteratively solving a constrained optimization problem can be framed as the temporal…

Machine Learning · Computer Science 2025-01-28 Tianqi Zhang , Puzhen Yuan , Guojian Zhan , Ziyu Lin , Yao Lyu , Zhenzhi Qin , Jingliang Duan , Liping Zhang , Shengbo Eben Li

This paper presents two new techniques relating to inexact solution of subproblems in augmented Lagrangian methods for convex programming. The first involves combining a relative error criterion for solution of the subproblems with over- or…

Optimization and Control · Mathematics 2025-09-17 Jonathan Eckstein , Chang Yu

In this paper, we develop a novel primal-dual semismooth Newton method for solving linearly constrained multi-block convex composite optimization problems. First, a differentiable augmented Lagrangian (AL) function is constructed by…

Optimization and Control · Mathematics 2024-05-17 Zhanwang Deng , Kangkang Deng , Jiang Hu , Zaiwen Wen

This paper explores the realm of infinite horizon average reward Constrained Markov Decision Processes (CMDPs). To the best of our knowledge, this work is the first to delve into the regret and constraint violation analysis of average…

Machine Learning · Computer Science 2024-10-31 Qinbo Bai , Washim Uddin Mondal , Vaneet Aggarwal

We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the unichain assumption and general policy parameterizations. Existing regret analyses for constrained reinforcement learning largely rely on…

Machine Learning · Computer Science 2026-02-10 Anirudh Satheesh , Vaneet Aggarwal

In this paper, we present a two-phase augmented Lagrangian method, called QSDPNAL, for solving convex quadratic semidefinite programming (QSDP) problems with constraints consisting of a large number of linear equality, inequality…

Optimization and Control · Mathematics 2017-01-02 Xudong Li , Defeng Sun , Kim-Chuan Toh

Nonlinearly constrained nonconvex and nonsmooth optimization models play an increasingly important role in machine learning, statistics and data analytics. In this paper, based on the augmented Lagrangian function we introduce a flexible…

Optimization and Control · Mathematics 2020-07-27 Daoli Zhu , Lei Zhao , Shuzhong Zhang

Necessary optimality conditions in Lagrangian form and the sequential minimization framework are extended to mixed-integer nonlinear optimization, without any convexity assumptions. Building upon a recently developed notion of local…

Optimization and Control · Mathematics 2026-04-10 Alberto De Marchi

In recent years, Reinforcement Learning (RL) has been applied to real-world problems with increasing success. Such applications often require to put constraints on the agent's behavior. Existing algorithms for constrained RL (CRL) rely on…

Machine Learning · Computer Science 2023-03-07 Ted Moskovitz , Brendan O'Donoghue , Vivek Veeriah , Sebastian Flennerhag , Satinder Singh , Tom Zahavy

This work aims to minimize a continuously differentiable convex function with Lipschitz continuous gradient under linear equality constraints. The proposed inertial algorithm results from the discretization of the second-order primal-dual…

Optimization and Control · Mathematics 2022-08-03 Radu Ioan Bot , Ernö Robert Csetnek , Dang-Khoa Nguyen

We consider deterministic Markov decision processes (MDPs) and apply max-plus algebra tools to approximate the value iteration algorithm by a smaller-dimensional iteration based on a representation on dictionaries of value functions. The…

Machine Learning · Computer Science 2019-06-21 Francis Bach

Learning to Optimize (L2O) approaches, including algorithm unrolling, plug-and-play methods, and hyperparameter learning, have garnered significant attention and have been successfully applied to the Alternating Direction Method of…

Optimization and Control · Mathematics 2024-09-27 Ling Liang , Cameron Austin , Haizhao Yang

In this paper, we study representation formulas for finite-horizon optimal control problems with or without state constraints, unifying two different viewpoints: the Lagrangian and dynamic programming (DP) frameworks. In a recent work [1],…

Optimization and Control · Mathematics 2022-11-04 Yeoneung Kim , Insoon Yang
‹ Prev 1 4 5 6 7 8 10 Next ›