English
Related papers

Related papers: Frugality in second-order optimization: floating-p…

200 papers

Training deep neural networks for solving machine learning problems is one great challenge in the field, mainly due to its associated optimisation problem being highly non-convex. Recent developments have suggested that many training…

Machine Learning · Computer Science 2017-11-23 Hao Shen

Variational inequalities represent a broad class of problems, including minimization and min-max problems, commonly found in machine learning. Existing second-order and high-order methods for variational inequalities require precise…

We present the online Newton's method, a single-step second-order method for online nonconvex optimization. We analyze its performance and obtain a dynamic regret bound that is linear in the cumulative variation between round optima. We…

Optimization and Control · Mathematics 2020-12-11 Antoine Lesage-Landry , Joshua A. Taylor , Iman Shames

We develop a principled approach to obtain exact computer-aided worst-case guarantees on the performance of second-order optimization methods on classes of univariate functions. We first present a generic technique to derive interpolation…

Optimization and Control · Mathematics 2025-07-01 Anne Rubbens , Nizar Bousselmi , Julien M. Hendrickx , François Glineur

We consider the problem of efficiently computing the maximum likelihood estimator in Generalized Linear Models (GLMs) when the number of observations is much larger than the number of coefficients ($n \gg p \gg 1$). In this regime,…

Machine Learning · Statistics 2015-12-01 Murat A. Erdogdu

Superlinear convergence has been an elusive goal for black-box nonsmooth optimization. Even in the convex case, the subgradient method is very slow, and while some cutting plane algorithms, including traditional bundle methods, are popular…

Optimization and Control · Mathematics 2019-07-30 Adrian Lewis , Calvin Wylie

This paper studies stochastic minimization of a finite-sum loss $ F (\mathbf{x}) = \frac{1}{N} \sum_{\xi=1}^N f(\mathbf{x};\xi) $. In many real-world scenarios, the Hessian matrix of such objectives exhibits a low-rank structure on a batch…

Optimization and Control · Mathematics 2025-08-12 Yu Liu , Weibin Peng , Tianyu Wang , Jiajia Yu

Recent efforts to accelerate LLM pretraining have focused on computationally-efficient approximations that exploit second-order structure. This raises a key question for large-scale training: how much performance is forfeited by these…

Machine Learning · Computer Science 2026-04-21 Natalie Abreu , Nikhil Vyas , Sham Kakade , Depen Morwani

Quasi-Newton methods form an important class of methods for solving nonlinear optimization problems. In such methods, first order information is used to approximate the second derivative. The aim is to mimic the fast convergence that can be…

Optimization and Control · Mathematics 2025-02-20 Aban Ansari-Önnestam , Anders Forsgren

A q-Gauss-Newton algorithm is an iterative procedure that solves nonlinear unconstrained optimization problems based on minimization of the sum squared errors of the objective function residuals. Main advantage of the algorithm is that it…

Optimization and Control · Mathematics 2021-05-28 Danijela Protic , Miomir Stankovic

Any gradient descent optimization requires to choose a learning rate. With deeper and deeper models, tuning that learning rate can easily become tedious and does not necessarily lead to an ideal convergence. We propose a variation of the…

Machine Learning · Statistics 2018-04-10 Mathieu Ravaut , Satya Gorti

Many problems in geometric optics or convex geometry can be recast as optimal transport problems: this includes the far-field reflector problem, Alexandrov's curvature prescription problem, etc. A popular way to solve these problems…

Numerical Analysis · Mathematics 2017-03-08 Jun Kitagawa , Quentin Mérigot , Boris Thibert

An algorithm is proposed for solving optimization problems arising in neural network training for supervised learning. The unique feature of the algorithm is the use of an auxiliary loss, in addition to the original loss employed for model…

Optimization and Control · Mathematics 2026-05-11 Yunlang Zhu , Lingjun Guo , Zahra Khatti , Xiaoyi Qu , Chia-Yuan Wu , Lara Zebiane , Frank E. Curtis

We consider minimization of a smooth nonconvex objective function using an iterative algorithm based on Newton's method and the linear conjugate gradient algorithm, with explicit detection and use of negative curvature directions for the…

Optimization and Control · Mathematics 2018-11-14 Clément W. Royer , Michael O'Neill , Stephen J. Wright

In this paper, we propose a distributed second- order method for reinforcement learning. Our approach is the fastest in literature so-far as it outperforms state-of-the-art methods, including ADMM, by significant margins. We achieve this by…

Optimization and Control · Mathematics 2016-08-08 Rasul Tutunov , Haitham Bou-Ammar , Ali Jadbabaie

The goal of this paper is to study approaches to bridge the gap between first-order and second-order type methods for composite convex programs. Our key observations are: i) Many well-known operator splitting methods, such as…

Optimization and Control · Mathematics 2016-09-27 Xiantao Xiao , Yongfeng Li , Zaiwen Wen , Liwei Zhang

In this paper, we generalize (accelerated) Newton's method with cubic regularization under inexact second-order information for (strongly) convex optimization problems. Under mild assumptions, we provide global rate of convergence of these…

Optimization and Control · Mathematics 2017-10-17 Saeed Ghadimi , Han Liu , Tong Zhang

Inspired by multigrid methods for linear systems of equations, multilevel optimization methods have been proposed to solve structured optimization problems. Multilevel methods make more assumptions regarding the structure of the…

Optimization and Control · Mathematics 2019-11-27 Chin Pang Ho , Michal Kocvara , Panos Parpas

Second-order methods for neural network optimization have several advantages over methods based on first-order gradient descent, including better scaling to large mini-batch sizes and fewer updates needed for convergence. But they are…

Machine Learning · Computer Science 2017-12-21 Huishuai Zhang , Caiming Xiong , James Bradbury , Richard Socher

A new variant of Newton's method for empirical risk minimization is studied, where at each iteration of the optimization algorithm, the gradient and Hessian of the objective function are replaced by robust estimators taken from existing…

Machine Learning · Statistics 2023-07-18 Eirini Ioannou , Muni Sreenivas Pydi , Po-Ling Loh