English
Related papers

Related papers: Fast Approximation of Rotations and Hessians matri…

200 papers

Sketching is a dimensionality reduction technique where one compresses a matrix by linear combinations that are chosen at random. A line of work has shown how to sketch the Hessian to speed up each iteration in a second order method, but…

Machine Learning · Computer Science 2021-10-07 Yi Li , Honghao Lin , David P. Woodruff

Low-rank approximation of a matrix by means of structured random sampling has been consistently efficient in its extensive empirical studies around the globe, but adequate formal support for this empirical phenomenon has been missing so…

Numerical Analysis · Mathematics 2016-07-21 Victor Pan , John Svadlenka , Liang Zhao

Matrix approximation is a common tool in machine learning for building accurate prediction models for recommendation systems, text mining, and computer vision. A prevalent assumption in constructing matrix approximations is that the…

Machine Learning · Computer Science 2013-01-16 Joonseok Lee , Seungyeon Kim , Guy Lebanon , Yoram Singer

Machine learning (ML) problems are often posed as highly nonlinear and nonconvex unconstrained optimization problems. Methods for solving ML problems based on stochastic gradient descent are easily scaled for very large problems but may…

Numerical Analysis · Mathematics 2019-05-24 Jennifer B. Erway , Joshua Griffin , Roummel F. Marcia , Riadh Omheni

In this article we present a machine learning model to obtain fast and accurate estimates of the molecular Hessian matrix. In this model, based on a random forest, the second derivatives of the energy with respect to redundant internal…

Chemical Physics · Physics 2024-01-10 Giorgio Domenichini , Christoph Dellago

In unconstrained maximum a posteriori (MAP) and maximum likelihood estimation, the inverse of minus the merit-function Hessian matrix is an approximation of the estimate covariance matrix. In the Bayesian context of MAP estimation, it is…

Methodology · Statistics 2020-03-17 Dimas Abreu Archanjo Dutra

In computational and applied statistics, it is of great interest to get fast and accurate calculation for the distributions of the quadratic forms of Gaussian random variables. This paper presents a novel approximation strategy that…

Methodology · Statistics 2023-12-29 Hong Zhang , Judong Shen , Zheyang Wu

Fast approximations to matrix multiplication have the potential to dramatically reduce the cost of neural network inference. Recent work on approximate matrix multiplication proposed to replace costly multiplications with table-lookups by…

Machine Learning · Computer Science 2022-07-14 Calvin McCarter , Nicholas Dronen

We are concerned with an approximation problem for a symmetric positive semidefinite matrix due to motivation from a class of nonlinear machine learning methods. We discuss an approximation approach that we call {matrix ridge…

Machine Learning · Statistics 2013-12-18 Zhihua Zhang

We propose an inexact variable-metric proximal point algorithm to accelerate gradient-based optimization algorithms. The proposed scheme, called QNing can be notably applied to incremental first-order methods such as the stochastic…

Machine Learning · Statistics 2019-01-30 Hongzhou Lin , Julien Mairal , Zaid Harchaoui

Successive quadratic approximations, or second-order proximal methods, are useful for minimizing functions that are a sum of a smooth part and a convex, possibly nonsmooth part that promotes regularization. Most analyses of iteration…

Optimization and Control · Mathematics 2019-01-25 Ching-pei Lee , Stephen J. Wright

We review the theory of, and develop algorithms for transforming a finite point set in ${\bf R}^d$ into a set in \emph{radial isotropic position} by a nonsingular linear transformation followed by rescaling each image point to the unit…

Computational Geometry · Computer Science 2020-05-12 Shiri Artstein-Avidan , Haim Kaplan , Micha Sharir

Several machine learning applications involve the optimization of higher-order derivatives (e.g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation. As a…

Machine Learning · Computer Science 2020-11-26 Tianyu Pang , Kun Xu , Chongxuan Li , Yang Song , Stefano Ermon , Jun Zhu

Object detection is a main task in computer vision. Template matching is the reference method for detecting objects with arbitrary templates. However, template matching computational complexity depends on the rotation accuracy, being a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-07 Antonio Martinez-Sanchez , Ulrike Homberg , José María Almira , Harold Phelippeau

This paper is concerned with the study of the embedding circulant matrix method to simulate stationary complex-valued Gaussian sequences. The method is, in particular, shown to be well-suited to generate circularly-symmetric stationary…

Statistics Theory · Mathematics 2016-04-04 Jean-Francois Coeurjolly , Emilio Porcu

We study online inference and asymptotic covariance estimation for the stochastic gradient descent (SGD) algorithm. While classical methods (such as plug-in and batch-means estimators) are available, they either require inaccessible…

Machine Learning · Statistics 2026-04-24 Ziyang Wei , Wanrong Zhu , Jingyang Lyu , Wei Biao Wu

This paper considers the problem of approximating the inverse of the wave-equation Hessian, also called normal operator, in seismology and other types of wave-based imaging. An expansion scheme for the pseudodifferential symbol of the…

Numerical Analysis · Mathematics 2015-03-17 Laurent Demanet , Pierre-David Létourneau , Nicolas Boumal , Henri Calandra , Jiawei Chiu , Stanley Snelson

We consider estimation of covariance matrices and their inverses (a.k.a. precision matrices) for high-dimensional stationary and locally stationary time series. In the latter case the covariance matrices evolve smoothly in time, thus…

Statistics Theory · Mathematics 2014-01-07 Xiaohui Chen , Mengyu Xu , Wei Biao Wu

We propose a new cross-conv algorithm for approximate computation of convolution in different low-rank tensor formats (tensor train, Tucker, Hierarchical Tucker). It has better complexity with respect to the tensor rank than previous…

Numerical Analysis · Mathematics 2016-09-07 M. V. Rakhuba , I. V. Oseledets

Several recent randomized linear algebra algorithms rely upon fast dimension reduction methods. A popular choice is the Subsampled Randomized Hadamard Transform (SRHT). In this article, we address the efficacy, in the Frobenius and spectral…

Data Structures and Algorithms · Computer Science 2015-03-20 Christos Boutsidis , Alex Gittens
‹ Prev 1 4 5 6 7 8 10 Next ›