English
Related papers

Related papers: An explicit analysis of the entropic penalty in li…

200 papers

The problems of Lasso regression and optimal design of experiments share a critical property: their optimal solutions are typically \emph{sparse}, i.e., only a small fraction of the optimal variables are non-zero. Therefore, the…

Methodology · Statistics 2023-12-07 Guillaume Sagnol , Luc Pronzato

Natural policy gradient (NPG) methods with entropy regularization achieve impressive empirical success in reinforcement learning problems with large state-action spaces. However, their convergence properties and the impact of entropy…

Machine Learning · Computer Science 2026-02-17 Semih Cayci , Niao He , R. Srikant

In this paper, we consider nonconvex optimization problems with nonlinear equality constraints. We assume that the objective function and the functional constraints are locally smooth. To solve this problem, we introduce a linearized…

Optimization and Control · Mathematics 2025-03-21 Lahcen El Bourkhissi , Ion Necoara

We propose new methods to speed up convergence of the Alternating Direction Method of Multipliers (ADMM), a common optimization tool in the context of large scale and distributed learning. The proposed method accelerates the speed of…

Machine Learning · Computer Science 2016-04-05 Changkyu Song , Sejong Yoon , Vladimir Pavlovic

Detectability of failures of linear programming (LP) decoding and the potential for improvement by adding new constraints motivate the use of an adaptive approach in selecting the constraints for the underlying LP problem. In this paper, we…

Information Theory · Computer Science 2007-07-13 Mohammad H. Taghavi , Paul H. Siegel

Augmented Lagrangian method (ALM) has been popularly used for solving constrained optimization problems. Practically, subproblems for updating primal variables in the framework of ALM usually can only be solved inexactly. The convergence…

Optimization and Control · Mathematics 2018-03-28 Yangyang Xu

We prove non asymptotic linear convergence rates for the constrained Anderson acceleration extrapolation scheme. These guarantees come from new upper bounds on the constrained Chebyshev problem, which consists in minimizing the maximum…

Numerical Analysis · Mathematics 2020-10-30 Mathieu Barré , Adrien Taylor , Alexandre d'Aspremont

The constrained minimization (respectively maximization) of directed distances and of related generalized entropies is a fundamental task in information theory as well as in the adjacent fields of statistics, machine learning, artificial…

Information Theory · Computer Science 2024-10-28 Michel Broniatowski , Wolfgang Stummer

Many recent applications in machine learning and data fitting call for the algorithmic solution of structured smooth convex optimization problems. Although the gradient descent method is a natural choice for this task, it requires exact…

Optimization and Control · Mathematics 2013-09-03 Anthony Man-Cho So

Large language models (LLMs) have demonstrated significant advancements in reasoning capabilities, performing well on various challenging benchmarks. Techniques like Chain-of-Thought prompting have been introduced to further improve…

Computation and Language · Computer Science 2025-06-13 Zehui Ling , Deshu Chen , Hongwei Zhang , Yifeng Jiao , Xin Guo , Yuan Cheng

We provide a new proof of the linear convergence of the alternating direction method of multipliers (ADMM) when one of the objective terms is strongly convex. Our proof is based on a framework for analyzing optimization algorithms…

Optimization and Control · Mathematics 2015-05-20 Robert Nishihara , Laurent Lessard , Benjamin Recht , Andrew Packard , Michael I. Jordan

This paper presents a general convergence theory of penalty based numerical methods for elliptic constrained inequality problems, including variational inequalities, hemivariational inequalities, and variational-hemivariational…

Numerical Analysis · Mathematics 2019-12-18 Weimin Han , Mircea Sofonea

In this paper we combine two existing approaches for approximating attractors. One of them approximates the attractors arbitrarily well by sublevel sets related to solutions of infinite dimensional linear programming problems. A downside…

Optimization and Control · Mathematics 2023-10-06 Corbinian Schlosser

This paper focuses on the design of sequential quadratic optimization (commonly known as SQP) methods for solving large-scale nonlinear optimization problems. The most computationally demanding aspect of such an approach is the computation…

Optimization and Control · Mathematics 2020-02-27 James V. Burke , Frank E. Curtis , Hao Wang , Jiashan Wang

In several implementations of Sequential Monte Carlo (SMC) methods it is natural, and important in terms of algorithmic efficiency, to exploit the information of the history of the samples to optimally tune their subsequent propagations. In…

Computation · Statistics 2014-02-07 Alexandros Beskos , Ajay Jasra , Nikolas Kantas , Alexandre Thiery

Constrained optimization problems appear in a wide variety of challenging real-world problems, where constraints often capture the physics of the underlying system. Classic methods for solving these problems rely on iterative algorithms…

Systems and Control · Electrical Eng. & Systems 2023-06-13 Meiyi Li , Soheil Kolouri , Javad Mohammadi

This paper studies semiparametric contextual bandits, a generalization of the linear stochastic bandit problem where the reward for an action is modeled as a linear function of known action features confounded by an non-linear…

Machine Learning · Statistics 2018-07-17 Akshay Krishnamurthy , Zhiwei Steven Wu , Vasilis Syrgkanis

Detectability of failures of linear programming (LP) decoding and its potential for improvement by adding new constraints motivate the use of an adaptive approach in selecting the constraints for the LP problem. In this paper, we make a…

Information Theory · Computer Science 2007-07-13 Mohammad H. Taghavi N. , Paul H. Siegel

Sparsity and rank functions are important ways of regularizing under-determined linear systems. Optimization of the resulting formulations is made difficult since both these penalties are non-convex and discontinuous. The most common remedy…

Optimization and Control · Mathematics 2019-01-01 Carl Olsson , Marcus Carlsson , Daniele Gerosa

We present a polynomial-time algorithm that obtains a set of Asymptotic Linear Programs (ALPs) from a given linear system S, such that one of these ALPs admits a feasible solution if and only if S admits a feasible solution. We also show…

Computational Complexity · Computer Science 2012-06-20 Deepak Ponvel Chermakani