English
Related papers

Related papers: Scalable Second Order Optimization for Deep Learni…

200 papers

One of the most widely used methods for solving large-scale stochastic optimization problems is distributed asynchronous stochastic gradient descent (DASGD), a family of algorithms that result from parallelizing stochastic gradient descent…

Optimization and Control · Mathematics 2021-07-08 Zhengyuan Zhou , Panayotis Mertikopoulos , Nicholas Bambos , Peter W. Glynn , Yinyu Ye

Second-order methods hold significant promise for enhancing the convergence of deep neural network training; however, their large memory and computational demands have limited their practicality. Thus there is a need for scalable…

Machine Learning · Computer Science 2023-11-17 Fnu Devvrit , Sai Surya Duvvuri , Rohan Anil , Vineet Gupta , Cho-Jui Hsieh , Inderjit Dhillon

The goal of decentralized optimization over a network is to optimize a global objective formed by a sum of local (possibly nonsmooth) convex functions using only local computation and communication. It arises in various application domains,…

Optimization and Control · Mathematics 2015-03-17 John Duchi , Alekh Agarwal , Martin Wainwright

The second-order optimization methods, notably the D-KFAC (Distributed Kronecker Factored Approximate Curvature) algorithms, have gained traction on accelerating deep neural network (DNN) training on GPU clusters. However, existing D-KFAC…

Machine Learning · Computer Science 2022-07-01 Lin Zhang , Shaohuai Shi , Wei Wang , Bo Li

We study distributed algorithms for expected loss minimization where the datasets are large and have to be stored on different machines. Often we deal with minimizing the average of a set of convex functions where each function is the…

Machine Learning · Computer Science 2019-07-24 Samira Sheikhi

We argue that current definitions of machine unlearning are underspecified for second-order optimizers. We compare first-order and second-order learners for their ability to handle the data deletion task with varying degrees of…

Machine Learning · Computer Science 2026-04-28 Kennon Stewart

Bilevel optimization, crucial for hyperparameter tuning, meta-learning and reinforcement learning, remains less explored in the decentralized learning paradigm, such as decentralized federated learning (DFL). Typically, decentralized…

Machine Learning · Computer Science 2024-10-21 Min Wen , Chengchang Liu , Ahmed Abdelmoniem , Yipeng Zhou , Yuedong Xu

Gradient dominance property is a condition weaker than strong convexity, yet sufficiently ensures global convergence even in non-convex optimization. This property finds wide applications in machine learning, reinforcement learning (RL),…

Optimization and Control · Mathematics 2024-05-30 Jiyuan Tan , Chenyu Xue , Chuwen Zhang , Qi Deng , Dongdong Ge , Yinyu Ye

We show that, for finite-sum minimization problems, incorporating partial second-order information of the objective function can dramatically improve the robustness to mini-batch size of variance-reduced stochastic gradient methods, making…

Optimization and Control · Mathematics 2024-04-24 Sachin Garg , Albert S. Berahas , Michał Dereziński

We study the problem of minimizing the sum of potentially non-differentiable convex cost functions with partially overlapping dependences in an asynchronous manner, where communication in the network is not coordinated. We study the…

Optimization and Control · Mathematics 2021-02-17 Yankai Lin , Iman Shames , Dragan Nesic

Backpropagation (BP) is the standard algorithm for training the deep neural networks that power modern artificial intelligence including large language models. However, BP is energy inefficient and unlikely to be implemented by the brain.…

Machine Learning · Computer Science 2025-10-30 Francesco Innocenti

The convolutional neural networks (CNNs) are generally trained using stochastic gradient descent (SGD) based optimization techniques. The existing SGD optimizers generally suffer with the overshooting of the minimum and oscillation near…

Machine Learning · Computer Science 2022-09-20 Shiv Ram Dubey , S. H. Shabbeer Basha , Satish Kumar Singh , Bidyut Baran Chaudhuri

Decentralized solutions to finite-sum minimization are of significant importance in many signal processing, control, and machine learning applications. In such settings, the data is distributed over a network of arbitrarily-connected nodes…

Machine Learning · Computer Science 2019-11-14 Ran Xin , Soummya Kar , Usman A. Khan

In machine learning, there is a fundamental trade-off between ease of optimization and expressive power. Neural Networks, in particular, have enormous expressive power and yet are notoriously challenging to train. The nature of that…

Machine Learning · Computer Science 2015-11-24 Diogo Almeida , Nate Sauder

In machine learning, asynchronous parallel stochastic gradient descent (APSGD) is broadly used to speed up the training process through multi-workers. Meanwhile, the time delay of stale gradients in asynchronous algorithms is generally…

Machine Learning · Computer Science 2020-06-09 Lifu Wang , Bo Shen , Ning Zhao

Stochastic gradient algorithms have been the main focus of large-scale learning problems and they led to important successes in machine learning. The convergence of SGD depends on the careful choice of learning rate and the amount of the…

Machine Learning · Computer Science 2015-11-03 Caglar Gulcehre , Marcin Moczulski , Yoshua Bengio

First-order methods for solving convex optimization problems have been at the forefront of mathematical optimization in the last 20 years. The rapid development of this important class of algorithms is motivated by the success stories…

Optimization and Control · Mathematics 2021-01-07 Pavel Dvurechensky , Mathias Staudigl , Shimrit Shtern

Despite the notable success of deep neural networks (DNNs) in solving complex tasks, the training process still remains considerable challenges. A primary obstacle is the substantial time required for training, particularly as high…

Machine Learning · Computer Science 2025-09-09 Viet Hoang Pham , Hyo-Sung Ahn

The fields of machine learning and mathematical optimization increasingly intertwined. The special topic on supervised learning and convex optimization examines this interplay. The training part of most supervised learning algorithms can…

Machine Learning · Computer Science 2015-07-14 Nan Wang

This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update with a vector of…

Machine Learning · Computer Science 2019-12-16 Andrew Jacobsen , Matthew Schlegel , Cameron Linke , Thomas Degris , Adam White , Martha White