English
Related papers

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

200 papers

In this paper, we consider the finite-state approximation of a discrete-time constrained Markov decision process (MDP) under the discounted and average cost criteria. Using the linear programming formulation of the constrained discounted…

Optimization and Control · Mathematics 2018-07-10 Naci Saldi

Despite the non-convexity of most modern machine learning parameterizations, Lagrangian duality has become a popular tool for addressing constrained learning problems. We revisit Augmented Lagrangian methods, which aim to mitigate the…

Machine Learning · Computer Science 2025-10-30 Ignacio Boero , Ignacio Hounie , Alejandro Ribeiro

The augmented Lagrangian method (ALM) is a classical optimization tool that solves a given "difficult" (constrained) problem via finding solutions of a sequence of "easier"(often unconstrained) sub-problems with respect to the original…

Optimization and Control · Mathematics 2020-04-16 Dusan Jakovetic , Dragana Bajovic , Joao Xavier , Jose M. F. Moura

We propose a distributed solution for a constrained convex optimization problem over a network of clustered agents each consisted of a set of subagents. The communication range of the clustered agents is such that they can form a connected…

Multiagent Systems · Computer Science 2021-04-06 Hossein Moradian , Solmaz S. Kia

The Augmented Lagrangian Method as an approach for regularizing inverse problems received much attention recently, e.g. under the name Bregman iteration in imaging. This work shows convergence (rates) for this method when Morozov's…

Numerical Analysis · Mathematics 2012-04-19 Klaus Frick , Dirk A. Lorenz , Elena Resmerita

Lagrangian Relaxation (LR) is a powerful technique for solving large-scale Mixed Integer Linear Programming (MILP), particularly those with decomposable structures, such as vehicle routing or unit commitment problems. By relaxing the…

Machine Learning · Statistics 2026-05-27 Tung Quoc Le , Anh Tuan Nguyen , Viet Anh Nguyen

Designing control policies for large, distributed systems is challenging, especially in the context of critical, temporal logic based specifications (e.g., safety) that must be met with high probability. Compositional methods for such…

Systems and Control · Electrical Eng. & Systems 2024-10-08 Krishna C. Kalagarla , Matthew Low , Rahul Jain , Ashutosh Nayyar , Pierluigi Nuzzo

Recent work has shown how information theory extends conventional full-rationality game theory to allow bounded rational agents. The associated mathematical framework can be used to solve constrained optimization problems. This is done by…

Neural and Evolutionary Computing · Computer Science 2008-11-07 William Macready , David Wolpert

We study a primal-dual (PD) reinforcement learning (RL) algorithm for online constrained Markov decision processes (CMDPs). Despite its widespread practical use, the existing theoretical literature on PD-RL algorithms for this problem only…

Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which…

Artificial Intelligence · Computer Science 2020-02-28 Tomas Brazdil , Krishnendu Chatterjee , Petr Novotny , Jiri Vahala

Incremental gradient and incremental proximal methods are a fundamental class of optimization algorithms used for solving finite sum problems, broadly studied in the literature. Yet, without strong convexity, their convergence guarantees…

Optimization and Control · Mathematics 2024-07-01 Xufeng Cai , Jelena Diakonikolas

We propose an inexact proximal augmented Lagrangian framework with explicit inner problem termination rule for composite convex optimization problems. We consider arbitrary linearly convergent inner solver including in particular stochastic…

Optimization and Control · Mathematics 2019-09-23 Fei Li , Zheng Qu

We revisit the finite time analysis of policy gradient methods in the one of the simplest settings: finite state and action MDPs with a policy class consisting of all stochastic policies and with exact gradient evaluations. There has been…

Machine Learning · Computer Science 2021-12-14 Jalaj Bhandari , Daniel Russo

We present a numerical method for the minimization of objectives that are augmented with large quadratic penalties of overdetermined inconsistent equality constraints. Such objectives arise from quadratic integral penalty methods for the…

Optimization and Control · Mathematics 2020-09-15 Martin P. Neuenhofen , Eric C. Kerrigan

First-order methods have been studied for nonlinear constrained optimization within the framework of the augmented Lagrangian method (ALM) or penalty method. We propose an improved inexact ALM (iALM) and conduct a unified analysis for…

Optimization and Control · Mathematics 2021-03-25 Zichong Li , Pin-Yu Chen , Sijia Liu , Songtao Lu , Yangyang Xu

We develop two new variants of alternating direction methods of multipliers (ADMM) and two parallel primal-dual decomposition algorithms to solve a wide range class of constrained convex optimization problems. Our approach relies on a novel…

Optimization and Control · Mathematics 2018-06-15 Quoc Tran-Dinh , Yuzixuan Zhu

The objective of this paper is to introduce and demonstrate a robust method for multi-constrained topology optimization. The method is derived by combining the topological sensitivity with the classic augmented Lagrangian formulation. The…

Computational Engineering, Finance, and Science · Computer Science 2022-03-31 Shiguang Deng , Krishnan Suresh

This paper addresses a class of general nonsmooth and nonconvex composite optimization problems subject to nonlinear equality constraints. We assume that a part of the objective function and the functional constraints exhibit local…

Optimization and Control · Mathematics 2025-03-04 Lahcen El Bourkhissi , Ion Necoara , Panagiotis Patrinos , Quoc Tran-Dinh

We propose a variant of the classical augmented Lagrangian method for constrained optimization problems in Banach spaces. Our theoretical framework does not require any convexity or second-order assumptions and allows the treatment of…

Optimization and Control · Mathematics 2018-07-13 Christian Kanzow , Daniel Steck , Daniel Wachsmuth

We derive a novel asymptotic problem-dependent lower-bound for regret minimization in finite-horizon tabular Markov Decision Processes (MDPs). While, similar to prior work (e.g., for ergodic MDPs), the lower-bound is the solution to an…

Machine Learning · Computer Science 2021-06-25 Andrea Tirinzoni , Matteo Pirotta , Alessandro Lazaric