English
Related papers

Related papers: Conditionally adaptive augmented Lagrangian method…

200 papers

A common formulation of constrained reinforcement learning involves multiple rewards that must individually accumulate to given thresholds. In this class of problems, we show a simple example in which the desired optimal policy cannot be…

Machine Learning · Computer Science 2023-09-22 Miguel Calvo-Fullana , Santiago Paternain , Luiz F. O. Chamon , Alejandro Ribeiro

Differential Dynamic Programming (DDP) has become a well established method for unconstrained trajectory optimization. Despite its several applications in robotics and controls however, a widely successful constrained version of the…

Optimization and Control · Mathematics 2020-05-05 Yuichiro Aoyama , George Boutselis , Akash Patel , Evangelos A. Theodorou

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in…

Computation and Language · Computer Science 2025-11-03 Daniel Israel , Guy Van den Broeck , Aditya Grover

The augmented Lagrangian method (ALM) has gained tremendous popularity for its elegant theory and impressive numerical performance since it was proposed by Hestenes and Powell in 1969. It has been widely used in numerous efficient solvers…

Optimization and Control · Mathematics 2022-08-09 Shiwei Wang , Chao Ding

In this paper, we adopt the augmented Lagrangian method (ALM) to solve convex quadratic second-order cone programming problems (SOCPs). Fruitful results on the efficiency of the ALM have been established in the literature. Recently, it has…

Optimization and Control · Mathematics 2021-10-26 Ling Liang , Defeng Sun , Kim-Chuan Toh

Regularization is a critical component in deep learning. The most commonly used approach, weight decay, applies a constant penalty coefficient uniformly across all parameters. This may be overly restrictive for some parameters, while…

Machine Learning · Computer Science 2024-12-10 Jörg K. H. Franke , Michael Hefenbrock , Gregor Koehler , Frank Hutter

Convex quadratic programs (QPs) constitute a fundamental computational primitive across diverse domains including financial optimization, control systems, and machine learning. The alternating direction method of multipliers (ADMM) has…

Optimization and Control · Mathematics 2025-05-15 Xi Gao , Jinxin Xiong , Linxin Yang , Akang Wang , Weiwei Xu , Jiang Xue

This paper proposes and establishes the iteration-complexity of an inexact proximal accelerated augmented Lagrangian (IPAAL) method for solving linearly constrained smooth nonconvex composite optimization problems. Each IPAAL iteration…

Optimization and Control · Mathematics 2020-06-16 Jefferson G. Melo , Renato D. C. Monteiro , Hairong Wang

This work studies the linear convergence of an accelerated scheme of the Alternating Direction Method of Multipliers (ADMM) for strongly convex and Lipschitz-smooth problems. We use the methodology of expressing the accelerated ADMM as a…

Optimization and Control · Mathematics 2025-12-08 Meisam Tavakoli , Fabian Jakob , Guido Carnevale , Giuseppe Notarstefano , Andrea Iannelli

We develop a unified theory of augmented Lagrangians for nonconvex optimization problems that encompasses both duality theory and convergence analysis of primal-dual augmented Lagrangian methods in the infinite dimensional setting. Our goal…

Optimization and Control · Mathematics 2025-09-09 M. V. Dolgopolik

We consider the minimization of a sum of a smooth function with a nonsmooth composite function, where the composition is applied on a random linear mapping. This random composite model encompasses many problems, and can especially capture…

Optimization and Control · Mathematics 2024-12-02 Dan Greenstein , Nadav Hallak

We propose QPALM, a nonconvex quadratic programming (QP) solver based on the proximal augmented Lagrangian method. This method solves a sequence of inner subproblems which can be enforced to be strongly convex and which therefore admit a…

Optimization and Control · Mathematics 2024-04-17 Ben Hermans , Andreas Themelis , Panagiotis Patrinos

In this paper, the alternating direction method of multipliers (ADMM) is investigated for distributed optimization problems in a networked multi-agent system. In particular, a new adaptive-gain ADMM algorithm is derived in a closed form and…

Systems and Control · Electrical Eng. & Systems 2020-02-26 Towfiq Rahman , Zhihua Qu , Toru Namerikawa

We propose a practical inexact augmented Lagrangian method (iALM) for nonconvex problems with nonlinear constraints. We characterize the total computational complexity of our method subject to a verifiable geometric condition, which is…

Optimization and Control · Mathematics 2022-04-22 Mehmet Fatih Sahin , Armin Eftekhari , Ahmet Alacaoglu , Fabian Latorre , Volkan Cevher

We propose a novel algorithm for solving non-convex, nonlinear equality-constrained finite-sum optimization problems. The proposed algorithm incorporates an additional sampling strategy for sample size update into the well-known framework…

Optimization and Control · Mathematics 2025-08-05 Nataša Krejić , Nataša Krklec Jerinkić , Tijana Ostojić , Nemanja Vučićević

This study investigates imposing hard inequality constraints on the outputs of convolutional neural networks (CNN) during training. Several recent works showed that the theoretical and practical advantages of Lagrangian optimization over…

Computer Vision and Pattern Recognition · Computer Science 2023-08-31 Hoel Kervadec , Jose Dolz , Jing Yuan , Christian Desrosiers , Eric Granger , Ismail Ben Ayed

Physics-Informed Neural Networks (PINNs) have emerged as a powerful, mesh-free paradigm for solving partial differential equations (PDEs). However, they notoriously struggle with stiff, multi-scale, and nonlinear systems due to the inherent…

Machine Learning · Computer Science 2026-03-24 Julian Evan Chrisnanto , Nurfauzi Fadillah , Yulison Herry Chrisnanto

We seek to impose linear, equality constraints in feedforward neural networks. As top layer predictors are usually nonlinear, this is a difficult task if we seek to deploy standard convex optimization methods and strong duality. To overcome…

Machine Learning · Computer Science 2023-01-10 Anand Rangarajan , Pan He , Jaemoon Lee , Tania Banerjee , Sanjay Ranka

Given a dissimilarity matrix, the metric nearness problem is to find the nearest matrix of distances that satisfy the triangle inequalities. This problem has wide applications, such as sensor networks, image processing, and so on. But it is…

Optimization and Control · Mathematics 2022-11-03 Peipei Tang , Bo Jiang , Chengjing Wang

Partial differential equations (PDEs) with near singular solutions pose significant challenges for traditional numerical methods, particularly in complex geometries where mesh generation and adaptive refinement become computationally…

Numerical Analysis · Mathematics 2025-07-24 Yangtao Deng , Qiaolin He , Xiaoping Wang