English
Related papers

Related papers: Second-order Neural Network Training Using Complex…

200 papers

Optimizing smooth convex functions in stochastic settings, where only noisy estimates of gradients and Hessians are available, is a fundamental problem in optimization. While first-order methods possess a low per-iteration cost, their…

Statistics Theory · Mathematics 2026-02-06 Antoine Godichon-Baggioni , Bruno Portier , Guillaume Sallé

Stochastic Gradient Descent (SGD) has proven to be remarkably effective in optimizing deep neural networks that employ ever-larger numbers of parameters. Yet, improving the efficiency of large-scale optimization remains a vital and highly…

Machine Learning · Computer Science 2020-11-11 Frithjof Gressmann , Zach Eaton-Rosen , Carlo Luschi

Stochastic gradient descent (SGD) is a standard optimization method to minimize a training error with respect to network parameters in modern neural network learning. However, it typically suffers from proliferation of saddle points in the…

Machine Learning · Computer Science 2017-11-23 Haiping Huang , Taro Toyoizumi

A stochastic second-order trust region method is proposed, which can be viewed as a second-order extension of the trust-region-ish (TRish) algorithm proposed by Curtis et al. (INFORMS J. Optim. 1(3) 200-220, 2019). In each iteration, a…

Optimization and Control · Mathematics 2019-11-19 Frank E. Curtis , Rui Shi

In this contribution, we present the implementation of a second-order CASSCF algorithm in conjunction with the Cholesky decomposition of the two-electron repulsion integrals. The algorithm, called Norm-Extended Optimization, guarantees…

Chemical Physics · Physics 2021-04-09 Tommaso Nottoli , Jürgen Gauss , Filippo Lipparini

In this work, we develop first-order (Hessian-free) and zero-order (derivative-free) implementations of the Cubically regularized Newton method for solving general non-convex optimization problems. For that, we employ finite difference…

Optimization and Control · Mathematics 2023-09-06 Nikita Doikov , Geovani Nunes Grapiglia

This paper proposes a new family of algorithms for training neural networks (NNs). These are based on recent developments in the field of non-convex optimization, going under the general name of successive convex approximation (SCA)…

Machine Learning · Statistics 2017-06-16 Simone Scardapane , Paolo Di Lorenzo

In this paper, we generalize (accelerated) Newton's method with cubic regularization under inexact second-order information for (strongly) convex optimization problems. Under mild assumptions, we provide global rate of convergence of these…

Optimization and Control · Mathematics 2017-10-17 Saeed Ghadimi , Han Liu , Tong Zhang

Recently, we proposed to transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model the linear dependencies instead. We…

Machine Learning · Computer Science 2013-03-12 Tommi Vatanen , Tapani Raiko , Harri Valpola , Yann LeCun

We consider a scalar function depending on a numerical solution of an initial value problem, and its second-derivative (Hessian) matrix for the initial value. The need to extract the information of the Hessian or to solve a linear system…

Numerical Analysis · Mathematics 2020-07-09 Shin-ichi Ito , Takeru Matsuda , Yuto Miyatake

Distributed optimization is widely used in large-scale and privacy-preserving machine learning, where each agent stores a local objective and communicates only with its neighbors in a connected network. We study decentralized second-order…

We develop several new communication-efficient second-order methods for distributed optimization. Our first method, NEWTON-STAR, is a variant of Newton's method from which it inherits its fast local quadratic rate. However, unlike Newton's…

Machine Learning · Computer Science 2021-02-16 Rustem Islamov , Xun Qian , Peter Richtárik

In modern deep learning, highly subsampled stochastic approximation (SA) methods are preferred to sample average approximation (SAA) methods because of large data sets as well as generalization properties. Additionally, due to perceived…

Optimization and Control · Mathematics 2021-08-26 Thomas O'Leary-Roseberry , Nick Alger , Omar Ghattas

Precise representation of large-scale undirected network is the basis for understanding relations within a massive entity set. The undirected network representation task can be efficiently addressed by a symmetry non-negative latent factor…

Machine Learning · Computer Science 2022-03-09 Weiling Li , Xin Luo

We introduce a novel method to compute a rank $m$ approximation of the inverse of the Hessian matrix in the distributed regime. By leveraging the differences in gradients and parameters of multiple Workers, we are able to efficiently…

Machine Learning · Computer Science 2017-09-18 Sébastien M. R. Arnold , Chunming Wang

Classical numerical methods for solving partial differential equations suffer from the curse dimensionality mainly due to their reliance on meticulously generated spatio-temporal grids. Inspired by modern deep learning based techniques for…

Machine Learning · Statistics 2018-04-20 Maziar Raissi

We present novel algorithms for simulation optimization using random directions stochastic approximation (RDSA). These include first-order (gradient) as well as second-order (Newton) schemes. We incorporate both continuous-valued as well as…

Optimization and Control · Mathematics 2015-08-11 Prashanth L. A. , Shalabh Bhatnagar , Michael Fu , Steve Marcus

Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. The backpropagation (backprop) algorithm has long been the most widely used algorithm for gradient computation of…

Machine Learning · Statistics 2018-03-28 Tim Tsz-Kit Lau , Jinshan Zeng , Baoyuan Wu , Yuan Yao

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

Newton's method leverages curvature information to boost performance, and thus outperforms first-order methods for distributed learning problems. However, Newton's method is not practical in large-scale and heterogeneous learning…

Machine Learning · Computer Science 2024-12-18 Shuzhen Chen , Yuan Yuan , Youming Tao , Tianzhu Wang , Zhipeng Cai , Dongxiao Yu
‹ Prev 1 4 5 6 7 8 10 Next ›