English
Related papers

Related papers: A Progressive Batching L-BFGS Method for Machine L…

200 papers

We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a regular gradient step, and a corrective direction dictated by…

Machine Learning · Computer Science 2022-04-29 Yunfei Teng , Wenbo Gao , Francois Chalus , Anna Choromanska , Donald Goldfarb , Adrian Weller

The classical line search for learning rate (LR) tuning in the stochastic gradient descent (SGD) algorithm can tame the convergence slowdown due to data-sampling noise. In a federated setting, wherein the client heterogeneity introduces a…

Machine Learning · Computer Science 2025-10-28 Geetika , Somya Tyagi , Bapi Chatterjee

This work presents the convergence rate analysis of stochastic variants of the broad class of direct-search methods of directional type. It introduces an algorithm designed to optimize differentiable objective functions $f$ whose values can…

Optimization and Control · Mathematics 2020-03-09 Kwassi Joseph Dzahini

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

In this paper we analyze boosting algorithms in linear regression from a new perspective: that of modern first-order methods in convex optimization. We show that classic boosting algorithms in linear regression, namely the incremental…

Statistics Theory · Mathematics 2015-05-19 Robert M. Freund , Paul Grigas , Rahul Mazumder

We propose an extension of quasi-Newton methods, and investigate the convergence and the robustness properties of the proposed update formulae for the approximate Hessian matrix. Fletcher has studied a variational problem which derives the…

Computation · Statistics 2010-10-15 Takafumi Kanamori , Atsumi Ohara

First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks. Second-order methods, despite their better convergence rate, are rarely used in practice due to the…

Machine Learning · Computer Science 2019-09-26 Tianle Cai , Ruiqi Gao , Jikai Hou , Siyu Chen , Dong Wang , Di He , Zhihua Zhang , Liwei Wang

We propose a projected semi-stochastic gradient descent method with mini-batch for improving both the theoretical complexity and practical performance of the general stochastic gradient descent method (SGD). We are able to prove linear…

Machine Learning · Computer Science 2017-05-08 Jie Liu , Martin Takac

The most straightforward method to accelerate Stochastic Gradient Descent (SGD) computation is to distribute the randomly selected batch of inputs over multiple processors. To keep the distributed processors fully utilized requires…

Machine Learning · Computer Science 2020-01-06 Zhewei Yao , Amir Gholami , Daiyaan Arfeen , Richard Liaw , Joseph Gonzalez , Kurt Keutzer , Michael Mahoney

Batch normalization (BN) has become a critical component across diverse deep neural networks. The network with BN is invariant to positively linear re-scale transformation, which makes there exist infinite functionally equivalent networks…

Machine Learning · Computer Science 2022-06-07 Mingyang Yi

In this paper, we develop convergence analysis of a modified line search method for objective functions whose value is computed with noise and whose gradient estimates are inexact and possibly random. The noise is assumed to be bounded in…

Optimization and Control · Mathematics 2021-03-05 Albert S. Berahas , Liyuan Cao , Katya Scheinberg

Update formulas for the Hessian approximations in quasi-Newton methods such as BFGS can be derived as analytical solutions to certain nearest-matrix problems. In this article, we propose a similar idea for deriving new limited memory…

Optimization and Control · Mathematics 2024-03-06 Erik Berglund , Mikael Johansson

Modern deep neural networks often require distributed training with many workers due to their large size. As the number of workers increases, communication overheads become the main bottleneck in data-parallel minibatch stochastic gradient…

Machine Learning · Statistics 2024-11-07 Tim Tsz-Kit Lau , Weijian Li , Chenwei Xu , Han Liu , Mladen Kolar

We introduce Predictive Batch Scheduling (PBS), a novel training optimization technique that accelerates language model convergence by dynamically prioritizing high-loss samples during batch construction. Unlike curriculum learning…

Artificial Intelligence · Computer Science 2026-02-20 Sumedh Rasal

In this paper, we study greedy variants of quasi-Newton methods. They are based on the updating formulas from a certain subclass of the Broyden family. In particular, this subclass includes the well-known DFP, BFGS and SR1 updates. However,…

Optimization and Control · Mathematics 2021-06-02 Anton Rodomanov , Yurii Nesterov

Many practical optimization problems involve objective function values that are corrupted by unavoidable numerical errors. In smooth nonconvex optimization, quasi-Newton methods combined with line search are widely used due to their…

Optimization and Control · Mathematics 2026-03-12 Hiroki Hamaguchi , Naoki Marumo , Akiko Takeda

L-BFGS is a hill climbing method that is guarantied to converge only for convex problems. In computer graphics, it is often used as a black box solver for a more general class of non linear problems, including problems having many local…

Graphics · Computer Science 2015-08-13 Nicolas Ray , Dmitry Sokolov

Although the performance of popular optimization algorithms such as Douglas-Rachford splitting (DRS) and the ADMM is satisfactory in small and well-scaled problems, ill conditioning and problem size pose a severe obstacle to their reliable…

Optimization and Control · Mathematics 2024-04-17 Andreas Themelis , Lorenzo Stella , Panagiotis Patrinos

State-of-the-art methods for solving smooth optimization problems are nonlinear conjugate gradient, low memory BFGS, and Majorize-Minimize (MM) subspace algorithms. The MM subspace algorithm which has been introduced more recently has shown…

Optimization and Control · Mathematics 2016-08-24 Emilie Chouzenoux , Jean-Christophe Pesquet

We propose a new stochastic optimization framework for empirical risk minimization problems such as those that arise in machine learning. The traditional approaches, such as (mini-batch) stochastic gradient descent (SGD), utilize an…

Machine Learning · Statistics 2020-02-04 Kenji Kawaguchi , Haihao Lu