English
Related papers

Related papers: Jorge: Approximate Preconditioning for GPU-efficie…

200 papers

Optimization in machine learning, both theoretical and applied, is presently dominated by first-order gradient methods such as stochastic gradient descent. Second-order optimization methods, that involve second derivatives and/or second…

Machine Learning · Computer Science 2021-03-08 Rohan Anil , Vineet Gupta , Tomer Koren , Kevin Regan , Yoram Singer

Orthogonality constraints are ubiquitous in robust and probabilistic machine learning. Unfortunately, current optimizers are computationally expensive and do not scale to problems with hundreds or thousands of constraints. One notable…

Machine Learning · Computer Science 2026-02-17 Adrián Javaloy , Antonio Vergari

Second-order optimization methods, which leverage curvature information, offer faster and more stable convergence than first-order methods such as stochastic gradient descent (SGD) and Adam. However, their practical adoption is hindered by…

Emerging Technologies · Computer Science 2025-12-08 Saitao Zhang , Yubiao Luo , Shiqing Wang , Pushen Zuo , Yongxiang Li , Lunshuai Pan , Zheng Miao , Zhong Sun

Fine-tuning is powerful for adapting large language models to downstream tasks, but it often results in huge memory usages. A promising approach to mitigate this is using Zeroth-Order (ZO) optimization, which estimates gradients to replace…

Machine Learning · Computer Science 2024-10-15 Fei Wang , Li Shen , Liang Ding , Chao Xue , Ye Liu , Changxing Ding

Second-order optimization algorithms exhibit excellent convergence properties for training deep learning models, but often incur significant computation and memory overheads. This can result in lower training efficiency than the first-order…

Machine Learning · Computer Science 2023-08-07 Lin Zhang , Shaohuai Shi , Bo Li

Fast gradient-based optimization algorithms have become increasingly essential for the computationally efficient training of machine learning models. One technique is to multiply the gradient by a preconditioner matrix to produce a step,…

Machine Learning · Computer Science 2023-09-12 Isaac Liao , Rumen R. Dangovski , Jakob N. Foerster , Marin Soljačić

Score-based models have recently been introduced as a richer framework to model distributions in high dimensions and are generally more suitable for generative tasks. In score-based models, a generative task is formulated using a parametric…

Machine Learning · Computer Science 2023-02-07 Harsh Mishra , Jurijs Nazarovs , Manmohan Dogra , Sathya N. Ravi

In parallel simulation, convergence and parallelism are often seen as inherently conflicting objectives. Improved parallelism typically entails lighter local computation and weaker coupling, which unavoidably slow the global convergence.…

Graphics · Computer Science 2025-06-10 Lei Lan , Zixuan Lu , Chun Yuan , Weiwei Xu , Hao Su , Huamin Wang , Chenfanfu Jiang , Yin Yang

Preconditioning has long been a staple technique in optimization, often applied to reduce the condition number of a matrix and speed up the convergence of algorithms. Although there are many popular preconditioning techniques in practice,…

Optimization and Control · Mathematics 2022-11-08 Zhaonan Qu , Wenzhi Gao , Oliver Hinder , Yinyu Ye , Zhengyuan Zhou

Topology Optimization (TO), which maximizes structural robustness under material weight constraints, is becoming an essential step for the automatic design of mechanical parts. However, existing TO algorithms use the Finite Element Analysis…

Robotics · Computer Science 2022-04-14 Zherong Pan , Xifeng Gao , Kui Wu

Optimizing large-scale nonconvex problems, common in deep learning, demands balancing rapid convergence with computational efficiency. First-order (FO) optimizers, which serve as today's baselines, provide fast convergence and good…

Machine Learning · Computer Science 2025-09-30 Jiahe Chen , Ziye Ma

The adversarial subproblem in two-stage adaptive robust optimization (ARO), which identifies the worst-case uncertainty realization, is a major computational bottleneck. This difficulty is exacerbated when the recourse value function is…

Systems and Control · Electrical Eng. & Systems 2026-03-25 Zhiyi Zhou , Ján Drgoňa , Yury Dvorkin

Rapid advances in data collection and processing capabilities have allowed for the use of increasingly complex models that give rise to nonconvex optimization problems. These formulations, however, can be arbitrarily difficult to solve in…

Multiagent Systems · Computer Science 2020-04-01 Stefan Vlaski , Ali H. Sayed

Primal-Dual Hybrid Gradient (PDHG) and Alternating Direction Method of Multipliers (ADMM) are two widely-used first-order optimization methods. They reduce a difficult problem to simple subproblems, so they are easy to implement and have…

Optimization and Control · Mathematics 2019-09-10 Yanli Liu , Yunbei Xu , Wotao Yin

Second-order optimizers, maintaining a matrix termed a preconditioner, are superior to first-order optimizers in both theory and practice. The states forming the preconditioner and its inverse root restrict the maximum size of models…

Machine Learning · Computer Science 2025-01-13 Sike Wang , Pan Zhou , Jia Li , Hua Huang

A new technique of global optimization and its applications in particular to neural networks are presented. The algorithm is also compared to other global optimization algorithms such as Gradient descent (GD), Monte Carlo (MC), Genetic…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-12-18 Homayoun Valafar , Okan K. Ersoy , Faramarz Valafar

Second-order optimization approaches like the generalized Gauss-Newton method are considered more powerful as they utilize the curvature information of the objective function with preconditioning matrices. Albeit offering tempting…

Machine Learning · Computer Science 2024-02-06 Yongchang Hao , Yanshuai Cao , Lili Mou

Learning to optimize is an approach that leverages training data to accelerate the solution of optimization problems. Many approaches use unrolling to parametrize the update step and learn optimal parameters. Although L2O has shown…

Optimization and Control · Mathematics 2025-07-15 Patrick Fahy , Mohammad Golbabaee , Matthias J. Ehrhardt

First-order stochastic methods are the state-of-the-art in large-scale machine learning optimization owing to efficient per-iteration complexity. Second-order methods, while able to provide faster convergence, have been much less explored…

Machine Learning · Statistics 2017-12-01 Naman Agarwal , Brian Bullins , Elad Hazan

Neural network training requires a large amount of computation and thus GPUs are often used for the acceleration. While they improve the performance, GPUs are underutilized during the training.This paper proposes out-of-order (ooo)…

Machine Learning · Computer Science 2021-10-05 Hyungjun Oh , Hyungjun Oh , HyeongJu Kim , Jiwon Seo
‹ Prev 1 2 3 10 Next ›