English
Related papers

Related papers: A New Multipoint Symmetric Secant Method with a De…

200 papers

Stochastic gradient descent and other first-order variants, such as Adam and AdaGrad, are commonly used in the field of deep learning due to their computational efficiency and low-storage memory requirements. However, these methods do not…

Optimization and Control · Mathematics 2025-02-19 Aditya Ranganath , Mukesh Singhal , Roummel Marcia

Recently several methods were proposed for sparse optimization which make careful use of second-order information [10, 28, 16, 3] to improve local convergence rates. These methods construct a composite quadratic approximation using Hessian…

Machine Learning · Computer Science 2015-07-15 Katya Scheinberg , Xiaocheng Tang

Scalable algorithms to solve optimization and regression tasks even approximately, are needed to work with large datasets. In this paper we study efficient techniques from matrix sketching to solve a variety of convex constrained regression…

Machine Learning · Computer Science 2019-11-01 Graham Cormode , Charlie Dickens

The limited memory steepest descent method (Fletcher, 2012) for unconstrained optimization problems stores a few past gradients to compute multiple stepsizes at once. We review this method and propose new variants. For strictly convex…

Optimization and Control · Mathematics 2024-04-17 Giulia Ferrandi , Michiel E. Hochstenbach

We propose a new method for low-rank approximation of Moore-Penrose pseudoinverses (MPPs) of large-scale matrices using tensor networks. The computed pseudoinverses can be useful for solving or preconditioning of large-scale overdetermined…

Numerical Analysis · Mathematics 2016-07-06 Namgil Lee , Andrzej Cichocki

We present two sampled quasi-Newton methods (sampled LBFGS and sampled LSR1) for solving empirical risk minimization problems that arise in machine learning. Contrary to the classical variants of these methods that sequentially build…

Optimization and Control · Mathematics 2021-07-29 Albert S. Berahas , Majid Jahani , Peter Richtárik , Martin Takáč

In this paper, we study structured quasi-Newton methods for optimization problems with orthogonality constraints. Note that the Riemannian Hessian of the objective function requires both the Euclidean Hessian and the Euclidean gradient. In…

Optimization and Control · Mathematics 2018-09-05 Jiang Hu , Bo Jiang , Lin Lin , Zaiwen Wen , Yaxiang Yuan

Progress in deep learning is slowed by the days or weeks it takes to train large models. The natural solution of using more hardware is limited by diminishing returns, and leads to inefficient use of additional resources. In this paper, we…

Machine Learning · Computer Science 2017-12-12 Shankar Krishnan , Ying Xiao , Rif A. Saurous

We present the marginal unbiased score expansion (MUSE) method, an algorithm for generic high-dimensional hierarchical Bayesian inference. MUSE performs approximate marginalization over arbitrary non-Gaussian latent parameter spaces,…

Cosmology and Nongalactic Astrophysics · Physics 2022-06-01 Marius Millea , Uros Seljak

In this work, we present a globalized stochastic semismooth Newton method for solving stochastic optimization problems involving smooth nonconvex and nonsmooth convex terms in the objective function. We assume that only noisy gradient and…

Optimization and Control · Mathematics 2018-03-12 Andre Milzarek , Xiantao Xiao , Shicong Cen , Zaiwen Wen , Michael Ulbrich

Training state-of-the-art (SOTA) deep models often requires extensive data, resulting in substantial training and storage costs. To address these challenges, dataset condensation has been developed to learn a small synthetic set that…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Hansong Zhang , Shikun Li , Pengju Wang , Dan Zeng , Shiming Ge

Powerful interior-point methods (IPM) based commercial solvers, such as Gurobi and Mosek, have been hugely successful in solving large-scale linear programming (LP) problems. The high efficiency of these solvers depends critically on the…

Optimization and Control · Mathematics 2020-03-20 Xudong Li , Defeng Sun , Kim-Chuan Toh

Iterative majorize-minimize (MM) (also called optimization transfer) algorithms solve challenging numerical optimization problems by solving a series of "easier" optimization problems that are constructed to guarantee monotonic descent of…

Computation · Statistics 2015-10-23 Madison G. McGaffin , Jeffrey A. Fessler

Unconstrained optimization problems become more common in scientific computing and engineering applications with the rapid development of artificial intelligence, and numerical methods for solving them more quickly and efficiently have been…

Optimization and Control · Mathematics 2025-04-17 Lin Li , Pengcheng Xie , Li Zhang

Reinforcement Learning (RL) algorithms allow artificial agents to improve their action selections so as to increase rewarding experiences in their environments. Deep Reinforcement Learning algorithms require solving a nonconvex and…

Machine Learning · Computer Science 2019-04-18 Jacob Rafati , Roummel F. Marcia

In this paper we consider multi-objective optimization problems over a box. The problem is very relevant and several computational approaches have been proposed in the literature. They broadly fall into two main classes: evolutionary…

Optimization and Control · Mathematics 2022-12-08 Matteo Lapucci , Pierluigi Mansueto , Fabio Schoen

Iterative Hessian sketch (IHS) is an effective sketching method for modeling large-scale data. It was originally proposed by Pilanci and Wainwright (2016; JMLR) based on randomized sketching matrices. However, it is computationally…

Machine Learning · Statistics 2020-03-10 Aijun Zhang , Hengtao Zhang , Guosheng Yin

The problem of minimizing a continuously differentiable convex function over an intersection of closed convex sets is ubiquitous in applied mathematics. It is particularly interesting when it is easy to project onto each separate set, but…

Optimization and Control · Mathematics 2014-08-06 Eric C. Chi , Hua Zhou , Kenneth Lange

Second-order optimization methods have desirable convergence properties. However, the exact Newton method requires expensive computation for the Hessian and its inverse. In this paper, we propose SPAN, a novel approximate and fast Newton…

Optimization and Control · Mathematics 2020-03-04 Xunpeng Huang , Xianfeng Liang , Zhengyang Liu , Yitan Li , Linyun Yu , Yue Yu , Lei Li

L-BFGS is the state-of-the-art optimization method for many large scale inverse problems. It has a small memory footprint and achieves superlinear convergence. The method approximates Hessian based on an initial approximation and an update…

Numerical Analysis · Mathematics 2021-03-19 Hari Om Aggrawal , Jan Modersitzki