中文
相关论文

相关论文: A Stochastic Implicit Proximal Point Algorithm for…

200 篇论文

In this paper, we propose a successive pseudo-convex approximation algorithm to efficiently compute stationary points for a large class of possibly nonconvex optimization problems. The stationary points are obtained by solving a sequence of…

最优化与控制 · 数学 2018-12-17 Yang Yang , Marius Pesavento

We propose a communication- and computation-efficient distributed optimization algorithm using second-order information for solving ERM problems with a nonsmooth regularization term. Current second-order and quasi-Newton methods for this…

最优化与控制 · 数学 2018-05-29 Ching-pei Lee , Cong Han Lim , Stephen J. Wright

We consider minimizing a function consisting of a quadratic term and a proximable term which is possibly nonconvex and nonsmooth. This problem is also known as scaled proximal operator. Despite its simple form, existing methods suffer from…

最优化与控制 · 数学 2024-03-01 Yiming Zhou , Wei Dai

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…

最优化与控制 · 数学 2022-11-03 Natasa Krejic , Natasa Krklec Jerinkic , Tijana Ostojic

We propose several new nonsmooth Newton methods for solving convex composite optimization problems with polyhedral regularizers, while avoiding the computation of complicated second-order information on these functions. Under the…

最优化与控制 · 数学 2025-11-25 Tran T. A. Nghia , Nghia V. Vo , Khoa V. H. Vu

We analyze two classical algorithms for solving additively composite convex optimization problems where the objective is the sum of a smooth term and a nonsmooth regularizer: proximal stochastic gradient method for a single regularizer; and…

最优化与控制 · 数学 2026-02-06 Kevin Kurian Thomas Vaidyan , Michael P. Friedlander , Ahmet Alacaoglu

We consider the problem of training a deep neural network with nonsmooth regularization to retrieve a sparse and efficient sub-structure. Our regularizer is only assumed to be lower semi-continuous and prox-bounded. We combine an adaptive…

机器学习 · 统计学 2022-06-20 Dounia Lakhmiri , Dominique Orban , Andrea Lodi

This paper proposes a stochastic variant of a classic algorithm---the cubic-regularized Newton method [Nesterov and Polyak 2006]. The proposed algorithm efficiently escapes saddle points and finds approximate local minima for general…

机器学习 · 计算机科学 2017-12-07 Nilesh Tripuraneni , Mitchell Stern , Chi Jin , Jeffrey Regier , Michael I. Jordan

We propose techniques for approximating bilevel optimization problems with non-smooth lower level problems that can have a non-unique solution. To this end, we substitute the expression of a minimizer of the lower level minimization problem…

最优化与控制 · 数学 2016-04-27 Peter Ochs , René Ranftl , Thomas Brox , Thomas Pock

We present a stochastic setting for optimization problems with nonsmooth convex separable objective functions over linear equality constraints. To solve such problems, we propose a stochastic Alternating Direction Method of Multipliers…

机器学习 · 计算机科学 2013-01-23 Hua Ouyang , Niao He , Alexander Gray

In this paper, we propose a class of penalty methods with stochastic approximation for solving stochastic nonlinear programming problems. We assume that only noisy gradients or function values of the objective function are available via…

最优化与控制 · 数学 2016-05-20 Xiao Wang , Shiqian Ma , Ya-xiang Yuan

Composite convex optimization problems which include both a nonsmooth term and a low-rank promoting term have important applications in machine learning and signal processing, such as when one wishes to recover an unknown matrix that is…

机器学习 · 计算机科学 2018-09-28 Dan Garber , Atara Kaplan

We propose an implicit iterative algorithm for an exact penalty method arising from inequality constrained optimization problems. A rapidly convergent fixed point method is developed for a regularized penalty functional. The applicability…

最优化与控制 · 数学 2012-10-05 Kazufumi Ito , Tomoya Takeuchi

Inspired by regularization techniques in statistics and machine learning, we study complementary composite minimization in the stochastic setting. This problem corresponds to the minimization of the sum of a (weakly) smooth function endowed…

机器学习 · 计算机科学 2024-01-24 Alexandre d'Aspremont , Cristóbal Guzmán , Clément Lezane

We consider the problem of minimizing a sum of several convex non-smooth functions. We introduce a new algorithm called the selective linearization method, which iteratively linearizes all but one of the functions and employs simple…

最优化与控制 · 数学 2016-08-16 Yu Du , Xiaodong Lin , Andrzej Ruszczynski

Stochastic nonconvex optimization problems with nonlinear constraints have a broad range of applications in intelligent transportation, cyber-security, and smart grids. In this paper, first, we propose an inexact-proximal accelerated…

最优化与控制 · 数学 2021-07-08 Morteza Boroun , Afrooz Jalilzadeh

In this paper, a novel stochastic extra-step quasi-Newton method is developed to solve a class of nonsmooth nonconvex composite optimization problems. We assume that the gradient of the smooth part of the objective function can only be…

最优化与控制 · 数学 2019-10-22 Minghan Yang , Andre Milzarek , Zaiwen Wen , Tong Zhang

Our work focuses on stochastic gradient methods for optimizing a smooth non-convex loss function with a non-smooth non-convex regularizer. Research on this class of problem is quite limited, and until recently no non-asymptotic convergence…

最优化与控制 · 数学 2019-05-15 Michael R. Metel , Akiko Takeda

Proximal methods are known to identify the underlying substructure of nonsmooth optimization problems. Even more, in many interesting situations, the output of a proximity operator comes with its structure at no additional cost, and…

最优化与控制 · 数学 2023-02-10 Gilles Bareilles , Franck Iutzeler , Jérôme Malick

In this paper, we consider high-dimensional nonconvex square-root-loss regression problems and introduce a proximal majorization-minimization (PMM) algorithm for these problems. Our key idea for making the proposed PMM to be efficient is to…

最优化与控制 · 数学 2020-05-28 Peipei Tang , Chengjing Wang , Defeng Sun , Kim-Chuan Toh