English
Related papers

Related papers: A Trust Region Method with Regularized Barzilai-Bo…

200 papers

Stochastic gradient-based optimization is crucial to optimize neural networks. While popular approaches heuristically adapt the step size and direction by rescaling gradients, a more principled approach to improve optimizers requires…

Machine Learning · Computer Science 2023-11-01 Philipp Dahlinger , Philipp Becker , Maximilian Hüttenrauch , Gerhard Neumann

The distributed optimization problem is set up in a collection of nodes interconnected via a communication network. The goal is to find the minimizer of a global objective function formed by the addition of partial functions locally known…

Optimization and Control · Mathematics 2022-06-07 Damián Marelli , Yong Xu , Minyue Fu , Zenghong Huang

The problem we consider is a multi-objective optimization problem, in which the goal is to find an optimal value of a vector function representing various criteria. The aim of this work is to develop an algorithm which utilizes the trust…

Optimization and Control · Mathematics 2026-05-15 Nataša Krejić , Nataša Krklec Jerinkić , Luka Rutešić

In this paper, we solve the l2-l1 sparse recovery problem by transforming the objective function of this problem into an unconstrained differentiable function and apply a limited-memory trust-region method. Unlike gradient projection-type…

Numerical Analysis · Mathematics 2016-03-01 Lasith Adhikari , Jennifer B. Erway , Shelby Lockhart , Roummel F. Marcia

We consider the minimization of non-convex functions that typically arise in machine learning. Specifically, we focus our attention on a variant of trust region methods known as cubic regularization. This approach is particularly attractive…

Machine Learning · Computer Science 2017-07-04 Jonas Moritz Kohler , Aurelien Lucchi

We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we develop a practical algorithm, called Trust Region Policy…

Machine Learning · Computer Science 2017-04-24 John Schulman , Sergey Levine , Philipp Moritz , Michael I. Jordan , Pieter Abbeel

In this paper, we consider to improve the stochastic variance reduce gradient (SVRG) method via incorporating the curvature information of the objective function. We propose to reduce the variance of stochastic gradients using the…

Optimization and Control · Mathematics 2022-08-24 Hardik Tankaria , Nobuo Yamashita

We present a novel derivative-free interpolation based optimization algorithm. A trust-region method is used where a surrogate model is realized via an interpolation framework. The framework for interpolation is provided by Universal…

Optimization and Control · Mathematics 2018-05-31 Tom Lefebvre , Frederik De Belie , Guillaume Crevecoeur

The generalized Lanczos trust-region (GLTR) method is one of the most popular approaches for solving large-scale trust-region subproblem (TRS). Recently, Jia and Wang [Z. Jia and F. Wang, \emph{SIAM J. Optim., 31 (2021), pp. 887--914}]…

Numerical Analysis · Mathematics 2023-06-27 Bo Feng , Gang Wu

A MATLAB implementation of the More-Sorensen sequential (MSS) method is presented. The MSS method computes the minimizer of a quadratic function defined by a limited-memory BFGS matrix subject to a two-norm trust-region constraint. This…

Numerical Analysis · Mathematics 2013-07-17 Jennifer B. Erway , Roummel F. Marcia

This work proposes a framework for large-scale stochastic derivative-free optimization (DFO) by introducing STARS, a trust-region method based on iterative minimization in random subspaces. This framework is both an algorithmic and…

Optimization and Control · Mathematics 2024-09-26 Kwassi Joseph Dzahini , Stefan M. Wild

Solving the trust-region subproblem (TRS) plays a key role in numerical optimization and many other applications. The generalized Lanczos trust-region (GLTR) method is a well-known Lanczos type approach for solving a large-scale TRS. The…

Numerical Analysis · Mathematics 2021-04-13 Zhongxiao Jia , Fa Wang

The goal of tensor completion is to fill in missing entries of a partially known tensor (possibly including some noise) under a low-rank constraint. This may be formulated as a least-squares problem. The set of tensors of a given…

Numerical Analysis · Mathematics 2018-12-03 Gennadij Heidel , Volker Schulz

A novel trust region method for solving linearly constrained nonlinear programs is presented. The proposed technique is amenable to a distributed implementation, as its salient ingredient is an alternating projected gradient sweep in place…

Optimization and Control · Mathematics 2015-08-04 Jean-Hubert Hours , Colin N. Jones

Bayesian Optimization (BO) has been widely applied to optimize expensive black-box functions while retaining sample efficiency. However, scaling BO to high-dimensional spaces remains challenging. Existing literature proposes performing…

Machine Learning · Computer Science 2025-08-27 Quanlin Chen , Yiyu Chen , Jing Huo , Tianyu Ding , Yang Gao , Yuetong Chen

We introduce a variant of the proximal gradient method in which the quadratic term is diagonal but may be indefinite, and is safeguarded by a trust region. Our method is a special case of the proximal quasi-Newton trust-region method of…

Optimization and Control · Mathematics 2023-09-18 Geoffroy Leconte , Dominique Orban

For quasi-Newton methods in unconstrained minimization, it is valuable to develop methods that are robust, i.e., methods that converge on a large number of problems. Trust-region algorithms are often regarded to be more robust than…

Optimization and Control · Mathematics 2023-12-13 Johannes J Brust , Philip E Gill

We propose a novel framework for analyzing convergence rates of stochastic optimization algorithms with adaptive step sizes. This framework is based on analyzing properties of an underlying generic stochastic process, in particular by…

Optimization and Control · Mathematics 2018-10-23 Jose Blanchet , Coralia Cartis , Matt Menickelly , Katya Scheinberg

We propose a new stepsize for the gradient method. It is shown that this new stepsize will converge to the reciprocal of the largest eigenvalue of the Hessian, when Dai-Yang's asymptotic optimal gradient method (Computational Optimization…

Optimization and Control · Mathematics 2019-05-13 Yakui Huang , Yu-Hong Dai , Xin-Wei Liu , Hongchao Zhang

In view of a direct and simple improvement of vanilla SGD, this paper presents a fine-tuning of its step-sizes in the mini-batch case. For doing so, one estimates curvature, based on a local quadratic model and using only noisy gradient…

Machine Learning · Computer Science 2022-02-10 Camille Castera , Jérôme Bolte , Cédric Févotte , Edouard Pauwels