English
Related papers

Related papers: Analytic natural gradient updates for Cholesky fac…

200 papers

We consider the problem of minimizing the average of a large number of smooth but possibly non-convex functions. In the context of most machine learning applications, each loss function is non-negative and thus can be expressed as the…

Optimization and Control · Mathematics 2024-07-08 Antonio Orvieto , Lin Xiao

In this paper, a gradient-free distributed algorithm is introduced to solve a set constrained optimization problem under a directed communication network. Specifically, at each time-step, the agents locally compute a so-called…

Optimization and Control · Mathematics 2021-09-06 Yipeng Pang , Guoqiang Hu

This paper proposes a stochastic gradient descent method with an adaptive Gaussian noise term for the global minimization of nearly convex functions, which are nonconvex and possess multiple strict local minimizers. The noise term,…

Optimization and Control · Mathematics 2025-08-05 Chenglong Bao , Liang Chen , Weizhi Shao

We introduce Kalman Gradient Descent, a stochastic optimization algorithm that uses Kalman filtering to adaptively reduce gradient variance in stochastic gradient descent by filtering the gradient estimates. We present both a theoretical…

Machine Learning · Statistics 2018-10-30 James Vuckovic

We cast Amari's natural gradient in statistical learning as a specific case of Kalman filtering. Namely, applying an extended Kalman filter to estimate a fixed unknown parameter of a probabilistic model from a series of observations, is…

Machine Learning · Statistics 2018-08-29 Yann Ollivier

We perform scalable approximate inference in continuous-depth Bayesian neural networks. In this model class, uncertainty about separate weights in each layer gives hidden units that follow a stochastic differential equation. We demonstrate…

Machine Learning · Statistics 2022-02-01 Winnie Xu , Ricky T. Q. Chen , Xuechen Li , David Duvenaud

This paper establishes a mathematical foundation for the Adam optimizer, elucidating its connection to natural gradient descent through Riemannian and information geometry. We provide an accessible and detailed analysis of the diagonal…

Machine Learning · Computer Science 2024-09-05 Dongseong Hwang

We introduce a general strategy for defining distributions over the space of sparse symmetric positive definite matrices. Our method utilizes the Cholesky factorization of the precision matrix, imposing sparsity through constraints on its…

Methodology · Statistics 2025-06-12 Gianluca Mastrantonio , Pierfrancesco Alaimo Di Loro , Marco Mingione

Gaussian variational approximations are widely used for summarizing posterior distributions in Bayesian models, especially in high-dimensional settings. However, a drawback of such approximations is the inability to capture skewness or more…

Methodology · Statistics 2026-04-02 Lucas Kock , Linda S. L. Tan , Prateek Bansal , David J. Nott

Standard first-order stochastic optimization algorithms base their updates solely on the average mini-batch gradient, and it has been shown that tracking additional quantities such as the curvature can help de-sensitize common…

Machine Learning · Computer Science 2020-11-11 Ricky T. Q. Chen , Dami Choi , Lukas Balles , David Duvenaud , Philipp Hennig

Some new rigorous perturbation bounds for the generalized Cholesky factorization with normwise or componentwise perturbations in the given matrix are obtained, where the componentwise perturbation has the form of backward rounding error for…

Numerical Analysis · Mathematics 2014-09-23 Hanyu Li , Yanfei Yang

We introduce optimization methods for convolutional neural networks that can be used to improve existing gradient-based optimization in terms of generalization error. The method requires only simple processing of existing stochastic…

Machine Learning · Computer Science 2020-08-26 Dong Lao , Peihao Zhu , Peter Wonka , Ganesh Sundaramoorthi

We study the estimation of the latent variable Gaussian graphical model (LVGGM), where the precision matrix is the superposition of a sparse matrix and a low-rank matrix. In order to speed up the estimation of the sparse plus low-rank…

Machine Learning · Statistics 2017-03-01 Pan Xu , Jian Ma , Quanquan Gu

Optimization problems with continuous data appear in, e.g., robust machine learning, functional data analysis, and variational inference. Here, the target function is given as an integral over a family of (continuously) indexed target…

Machine Learning · Computer Science 2023-11-01 Kexin Jin , Jonas Latz , Chenguang Liu , Carola-Bibiane Schönlieb

The adaptive $s$-step CG algorithm is a solver for sparse, symmetric positive definite linear systems designed to reduce the synchronization cost per iteration while still achieving a user-specified accuracy requirement. In this work, we…

Numerical Analysis · Mathematics 2019-08-13 Erin C. Carson

Many problems encountered in science and engineering can be formulated as estimating a low-rank object (e.g., matrices and tensors) from incomplete, and possibly corrupted, linear measurements. Through the lens of matrix and tensor…

Machine Learning · Computer Science 2023-10-11 Cong Ma , Xingyu Xu , Tian Tong , Yuejie Chi

We prove that Fisher-Rao natural gradient descent (FR-NGD) optimally approximates the continuous time replicator equation (an essential model of evolutionary dynamics), and term this correspondence "conjugate natural selection". This…

Machine Learning · Computer Science 2023-06-14 Reilly Raab , Luca de Alfaro , Yang Liu

The paper considers the problem of network-based computation of global minima in smooth nonconvex optimization problems. It is known that distributed gradient-descent-type algorithms can achieve convergence to the set of global minima by…

Optimization and Control · Mathematics 2019-10-24 Brian Swenson , Anirudh Sridhar , H. Vincent Poor

Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients at each iteration…

Machine Learning · Computer Science 2022-07-07 Ryuichi Ito , Seng Pei Liew , Tsubasa Takahashi , Yuya Sasaki , Makoto Onizuka

Stochastic gradient algorithms have been the main focus of large-scale learning problems and they led to important successes in machine learning. The convergence of SGD depends on the careful choice of learning rate and the amount of the…

Machine Learning · Computer Science 2015-11-03 Caglar Gulcehre , Marcin Moczulski , Yoshua Bengio