English
Related papers

Related papers: Large-Scale Distributed Second-Order Optimization …

200 papers

Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been…

Machine Learning · Statistics 2018-01-03 Elad Hoffer , Itay Hubara , Daniel Soudry

This article exposes the failure of some big neural networks to leverage added capacity to reduce underfitting. Past research suggest diminishing returns when increasing the size of neural networks. Our experiments on ImageNet LSVRC-2010…

Machine Learning · Computer Science 2013-03-18 Yann N. Dauphin , Yoshua Bengio

In this paper, we consider both first- and second-order techniques to address continuous optimization problems arising in machine learning. In the first-order case, we propose a framework of transition from deterministic or…

Machine Learning · Computer Science 2021-11-30 Sanae Lotfi , Tiphaine Bonniot de Ruisselet , Dominique Orban , Andrea Lodi

The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$-$512$ data points, is…

Machine Learning · Computer Science 2017-02-13 Nitish Shirish Keskar , Dheevatsa Mudigere , Jorge Nocedal , Mikhail Smelyanskiy , Ping Tak Peter Tang

We propose and analyze several inexact regularized Newton-type methods for finding a global saddle point of convex-concave unconstrained min-max optimization problems. Compared to first-order methods, our understanding of second-order…

Optimization and Control · Mathematics 2026-05-27 Tianyi Lin , Panayotis Mertikopoulos , Michael I. Jordan

Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and…

Machine Learning · Computer Science 2019-05-28 Sanjeev Arora , Simon S. Du , Wei Hu , Zhiyuan Li , Ruosong Wang

Differentially private (stochastic) gradient descent is the workhorse of DP private machine learning in both the convex and non-convex settings. Without privacy constraints, second-order methods, like Newton's method, converge faster than…

Machine Learning · Computer Science 2023-05-23 Arun Ganesh , Mahdi Haghifam , Thomas Steinke , Abhradeep Thakurta

Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance. Conventional wisdom attributes small generalization error either to properties of the…

Machine Learning · Computer Science 2017-02-28 Chiyuan Zhang , Samy Bengio , Moritz Hardt , Benjamin Recht , Oriol Vinyals

Training in supervised deep learning is computationally demanding, and the convergence behavior is usually not fully understood. We introduce and study a second-order stochastic quasi-Gauss-Newton (SQGN) optimization method that combines…

Machine Learning · Computer Science 2020-07-02 Christopher Thiele , Mauricio Araya-Polo , Detlef Hohl

This paper advances the computational efficiency of Deep Hedging frameworks through the novel integration of Kronecker-Factored Approximate Curvature (K-FAC) optimization. While recent literature has established Deep Hedging as a…

Statistical Finance · Quantitative Finance 2024-11-25 Tsogt-Ochir Enkhbayar

While first-order optimization methods such as stochastic gradient descent (SGD) are popular in machine learning (ML), they come with well-known deficiencies, including relatively-slow convergence, sensitivity to the settings of…

Optimization and Control · Mathematics 2018-02-19 Peng Xu , Farbod Roosta-Khorasani , Michael W. Mahoney

Feed-forward neural networks can be understood as a combination of an intermediate representation and a linear hypothesis. While most previous works aim to diversify the representations, we explore the complementary direction by performing…

Machine Learning · Computer Science 2019-10-24 Han Zhao , Yao-Hung Hubert Tsai , Ruslan Salakhutdinov , Geoffrey J. Gordon

Large-batch training has become a commonly used technique when training neural networks with a large number of GPU/TPU processors. As batch size increases, stochastic optimizers tend to converge to sharp local minima, leading to degraded…

Machine Learning · Computer Science 2022-01-25 Yong Liu , Xiangning Chen , Minhao Cheng , Cho-Jui Hsieh , Yang You

A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better accuracy. These advances come with practical challenges: for…

Machine Learning · Computer Science 2019-03-05 Jasmine Collins , Johannes Balle , Jonathon Shlens

Sequence models such as transformers require inputs to be represented as one-dimensional sequences. In vision, this typically involves flattening images using a fixed row-major (raster-scan) order. While full self-attention is…

Machine Learning · Computer Science 2025-10-24 Declan Kutscher , David M. Chan , Yutong Bai , Trevor Darrell , Ritwik Gupta

Second-order methods have shown state-of-the-art performance for optimizing deep neural networks. Nonetheless, their large memory requirement and high computational complexity, compared to first-order methods, hinder their versatility in a…

Machine Learning · Computer Science 2022-03-08 Ehsan Amid , Rohan Anil , Manfred K. Warmuth

In this work, we propose to progressively increase the training difficulty during learning a neural network model via a novel strategy which we call mini-batch trimming. This strategy makes sure that the optimizer puts its focus in the…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Hannes Fassold

We present a general technique for the analysis of first-order methods. The technique relies on the construction of a duality gap for an appropriate approximation of the objective function, where the function approximation improves as the…

Optimization and Control · Mathematics 2019-12-12 Jelena Diakonikolas , Lorenzo Orecchia

Mini-batch stochastic gradient methods (SGD) are state of the art for distributed training of deep neural networks. Drastic increases in the mini-batch sizes have lead to key efficiency and scalability gains in recent years. However,…

Machine Learning · Computer Science 2020-02-18 Tao Lin , Sebastian U. Stich , Kumar Kshitij Patel , Martin Jaggi

Neural networks have achieved remarkable success in many cognitive tasks. However, when they are trained sequentially on multiple tasks without access to old data, their performance on early tasks tend to drop significantly. This problem is…

Machine Learning · Computer Science 2021-02-10 Dong Yin , Mehrdad Farajtabar , Ang Li , Nir Levine , Alex Mott