English
Related papers

Related papers: Kronecker-factored Quasi-Newton Methods for Deep L…

200 papers

Functional near-infrared spectroscopy (fNIRS) is employed as a non-invasive method to monitor functional brain activation by capturing changes in the concentrations of oxygenated haemoglobin (HbO) and deoxygenated haemo-globin (HbR).…

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

Training neural networks with many processors can reduce time-to-solution; however, it is challenging to maintain convergence and efficiency at large scales. The Kronecker-factored Approximate Curvature (K-FAC) was recently proposed as an…

Machine Learning · Computer Science 2020-07-03 J. Gregory Pauloski , Zhao Zhang , Lei Huang , Weijia Xu , Ian T. Foster

Kronecker Products (KP) have been used to compress IoT RNN Applications by 15-38x compression factors, achieving better results than traditional compression methods. However when KP is applied to large Natural Language Processing tasks, it…

Machine Learning · Computer Science 2020-11-18 Urmish Thakker , Paul N. Whatmough , Zhi-Gang Liu , Matthew Mattina , Jesse Beu

We propose a novel second-order optimization framework for training the emerging deep continuous-time models, specifically the Neural Ordinary Differential Equations (Neural ODEs). Since their training already involves expensive gradient…

Machine Learning · Computer Science 2021-11-09 Guan-Horng Liu , Tianrong Chen , Evangelos A. Theodorou

Physics-informed machine learning and inverse modeling require the solution of ill-conditioned non-convex optimization problems. First-order methods, such as SGD and ADAM, and quasi-Newton methods, such as BFGS and L-BFGS, have been applied…

Numerical Analysis · Mathematics 2021-05-18 Kailai Xu , Eric Darve

We present two sampled quasi-Newton methods (sampled LBFGS and sampled LSR1) for solving empirical risk minimization problems that arise in machine learning. Contrary to the classical variants of these methods that sequentially build…

Optimization and Control · Mathematics 2021-07-29 Albert S. Berahas , Majid Jahani , Peter Richtárik , Martin Takáč

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

We propose an efficient method for approximating natural gradient descent in neural networks which we call Kronecker-Factored Approximate Curvature (K-FAC). K-FAC is based on an efficiently invertible approximation of a neural network's…

Machine Learning · Computer Science 2020-06-09 James Martens , Roger Grosse

In this paper we take a quasi-Newton approach to nonlinear eigenvalue problems (NEPs) of the type $M(\lambda)v=0$, where $M:\mathbb{C}\rightarrow\mathbb{C}^{n\times n}$ is a holomorphic function. We investigate which types of approximations…

Numerical Analysis · Mathematics 2017-03-01 Elias Jarlebring , Antti Koskela , Giampaolo Mele

Deep Convolutional Neural Networks (CNNs) have been widely used in various domains due to their impressive capabilities. These models are typically composed of a large number of 2D convolutional (Conv2D) layers with numerous trainable…

Machine Learning · Computer Science 2022-02-01 Yinan Yu , Samuel Scheidegger , Tomas McKelvey

Optimization problems, arise in many practical applications, from the view points of both theory and numerical methods. Especially, significant improvement in deep learning training came from the Quasi-Newton methods. Quasi-Newton search…

Optimization and Control · Mathematics 2024-11-19 Jiongcheng Li

Transformers excel at in-context learning (ICL) -- learning from demonstrations without parameter updates -- but how they do so remains a mystery. Recent work suggests that Transformers may internally run Gradient Descent (GD), a…

Machine Learning · Computer Science 2024-11-19 Deqing Fu , Tian-Qi Chen , Robin Jia , Vatsal Sharan

We propose a new per-layer adaptive step-size procedure for stochastic first-order optimization methods for minimizing empirical loss functions in deep learning, eliminating the need for the user to tune the learning rate (LR). The proposed…

Machine Learning · Computer Science 2023-07-07 Achraf Bahamou , Donald Goldfarb

Despite the predominant use of first-order methods for training deep learning models, second-order methods, and in particular, natural gradient methods, remain of interest because of their potential for accelerating training through the use…

Machine Learning · Computer Science 2021-12-23 Yi Ren , Donald Goldfarb

Multi-task learning is useful in NLP because it is often practically desirable to have a single model that works across a range of tasks. In the medical domain, sequential training on tasks may sometimes be the only way to train models,…

Computation and Language · Computer Science 2021-11-12 Denis Jered McInerney , Luyang Kong , Kristjan Arumae , Byron Wallace , Parminder Bhatia

Inspired by the recent work FedNL (Safaryan et al, FedNL: Making Newton-Type Methods Applicable to Federated Learning), we propose a new communication efficient second-order framework for Federated learning, namely FLECS. The proposed…

Optimization and Control · Mathematics 2022-06-07 Artem Agafonov , Dmitry Kamzolov , Rachael Tappenden , Alexander Gasnikov , Martin Takáč

Deep Learning using the eponymous deep neural networks (DNNs) has become an attractive approach towards various data-based problems of theoretical physics in the past decade. There has been a clear trend to deeper architectures containing…

Machine Learning · Computer Science 2021-06-30 Bastian Kaspschak , Ulf-G. Meißner

Given its widespread application in machine learning and optimization, the Kronecker product emerges as a pivotal linear algebra operator. However, its computational demands render it an expensive operation, leading to heightened costs in…

Data Structures and Algorithms · Computer Science 2024-02-14 Yeqi Gao , Zhao Song , Ruizhe Zhang

In this paper, we discuss the problem of minimizing the sum of two convex functions: a smooth function plus a non-smooth function. Further, the smooth part can be expressed by the average of a large number of smooth component functions, and…

Machine Learning · Computer Science 2016-11-17 Luo Luo , Zihao Chen , Zhihua Zhang , Wu-Jun Li