English
Related papers

Related papers: EA-CG: An Approximate Second-Order Method for Trai…

200 papers

Training of convolutional neural networks is a high dimensional and a non-convex optimization problem. At present, it is inefficient in situations where parametric learning rates can not be confidently set. Some past works have introduced…

Machine Learning · Computer Science 2023-04-06 Ujjwal Thakur , Anuj Sharma

Deep neural networks are usually trained with stochastic gradient descent (SGD), which minimizes objective function using very rough approximations of gradient, only averaging to the real gradient. Standard approaches like momentum or ADAM…

Machine Learning · Computer Science 2023-03-14 Jarek Duda

Catastrophic forgetting remains a major challenge when neural networks learn tasks sequentially. Elastic Weight Consolidation (EWC) attempts to address this problem by introducing a Bayesian-inspired regularization loss to preserve…

Machine Learning · Computer Science 2025-03-27 Steven Vander Eeckt , Hugo Van hamme

Training a neural network (NN) typically relies on some type of curve-following method, such as gradient descent (GD) (and stochastic gradient descent (SGD)), ADADELTA, ADAM or limited memory algorithms. Convergence for these algorithms…

Machine Learning · Computer Science 2023-05-08 Michael A Kouritzin , Stephen Styles , Beatrice-Helen Vritsiou

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 work, we investigate stochastic quasi-Newton methods for minimizing a finite sum of cost functions over a decentralized network. In Part I, we develop a general algorithmic framework that incorporates stochastic quasi-Newton…

Optimization and Control · Mathematics 2023-03-22 Jiaojiao Zhang , Huikang Liu , Anthony Man-Cho So , Qing Ling

Training neural networks is a challenging non-convex optimization problem, and backpropagation or gradient descent can get stuck in spurious local optima. We propose a novel algorithm based on tensor decomposition for guaranteed training of…

Machine Learning · Computer Science 2016-01-13 Majid Janzamin , Hanie Sedghi , Anima Anandkumar

We propose a new algorithm for finite sum optimization which we call the curvature-aided incremental aggregated gradient (CIAG) method. Motivated by the problem of training a classifier for a d-dimensional problem, where the number of…

Machine Learning · Statistics 2017-10-26 Hoi-To Wai , Wei Shi , Angelia Nedic , Anna Scaglione

A new method to represent and approximate rotation matrices is introduced. The method represents approximations of a rotation matrix $Q$ with linearithmic complexity, i.e. with $\frac{1}{2}n\lg(n)$ rotations over pairs of coordinates,…

Machine Learning · Computer Science 2014-04-30 Michael Mathieu , Yann LeCun

We propose a novel technique for faster deep neural network training which systematically applies sample-based approximation to the constituent tensor operations, i.e., matrix multiplications and convolutions. We introduce new sampling…

Machine Learning · Computer Science 2021-10-27 Menachem Adelman , Kfir Y. Levy , Ido Hakimi , Mark Silberstein

A common problem in training neural networks is the vanishing and/or exploding gradient problem which is more prominently seen in training of Recurrent Neural Networks (RNNs). Thus several algorithms have been proposed for training RNNs.…

Machine Learning · Computer Science 2019-09-10 S. Indrapriyadarsini , Shahrzad Mahboubi , Hiroshi Ninomiya , Hideki Asai

The Hessian-vector product has been utilized to find a second-order stationary solution with strong complexity guarantee (e.g., almost linear time complexity in the problem's dimensionality). In this paper, we propose to further reduce the…

Optimization and Control · Mathematics 2017-10-03 Mingrui Liu , Tianbao Yang

Large scale optimization problems are ubiquitous in machine learning and data analysis and there is a plethora of algorithms for solving such problems. Many of these algorithms employ sub-sampling, as a way to either speed up the…

Optimization and Control · Mathematics 2016-02-29 Farbod Roosta-Khorasani , Michael W. Mahoney

Conventional stochastic rounding (CSR) is widely employed in the training of neural networks (NNs), showing promising training results even in low-precision computations. We introduce an improved stochastic rounding method, that is simple…

Machine Learning · Computer Science 2021-03-26 Lu Xia , Martijn Anthonissen , Michiel Hochstenbach , Barry Koren

While first-order methods are popular for solving optimization problems that arise in large-scale deep learning problems, they come with some acute deficiencies. To diminish such shortcomings, there has been recent interest in applying…

Machine Learning · Computer Science 2023-10-05 Mahsa Yousefi , Angeles Martinez

In Part I of this work, we have proposed a general framework of decentralized stochastic quasi-Newton methods, which converge linearly to the optimal solution under the assumption that the local Hessian inverse approximations have bounded…

Optimization and Control · Mathematics 2022-01-20 Jiaojiao Zhang , Huikang Liu , Anthony Man-Cho So , Qing Ling

Stochastic second-order methods achieve fast local convergence in strongly convex optimization by using noisy Hessian estimates to precondition the gradient. However, these methods typically reach superlinear convergence only when the…

Optimization and Control · Mathematics 2024-11-12 Ruichen Jiang , Michał Dereziński , Aryan Mokhtari

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in recommender systems. Nevertheless, the process of searching and ranking from a large item corpus usually requires high latency, which limits the widespread…

Information Retrieval · Computer Science 2023-09-06 Huiyuan Chen , Kaixiong Zhou , Kwei-Herng Lai , Chin-Chia Michael Yeh , Yan Zheng , Xia Hu , Hao Yang

We introduce compositional tensor trains (CTTs) for the approximation of multivariate functions, a class of models obtained by composing low-rank functions in the tensor-train format. This format can encode standard approximation tools,…

Numerical Analysis · Mathematics 2025-12-23 Martin Eigel , Charles Miranda , Anthony Nouy , David Sommer

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