English
Related papers

Related papers: Analytic natural gradient updates for Cholesky fac…

200 papers

Accelerating the convergence of second-order optimization, particularly Newton-type methods, remains a pivotal challenge in algorithmic research. In this paper, we extend previous work on the \textbf{Quadratic Gradient (QG)} and rigorously…

Optimization and Control · Mathematics 2026-04-01 John Chiang

We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice. We demonstrate the effectiveness of the method in a range of optimization problems by…

Machine Learning · Computer Science 2018-08-23 Atilim Gunes Baydin , Robert Cornish , David Martinez Rubio , Mark Schmidt , Frank Wood

In this article, an efficient numerical method for computing both the matrix exponential and a finite horizon controllability Gramian in Cholesky-factored form is proposed. The method is applicable to general dense matrices of moderate size…

Numerical Analysis · Mathematics 2025-05-27 Tony Stillfjord , Filip Tronarp

The randomly pivoted partial Cholesky algorithm (RPCholesky) computes a factorized rank-k approximation of an N x N positive-semidefinite (psd) matrix. RPCholesky requires only (k + 1) N entry evaluations and O(k^2 N) additional arithmetic…

Numerical Analysis · Mathematics 2024-10-23 Yifan Chen , Ethan N. Epperly , Joel A. Tropp , Robert J. Webber

The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any…

Machine Learning · Statistics 2013-02-19 Tom Schaul , Sixin Zhang , Yann LeCun

In recent years, there has been widespread adoption of machine learning-based approaches to automate the solving of partial differential equations (PDEs). Among these approaches, Gaussian processes (GPs) and kernel methods have garnered…

Numerical Analysis · Mathematics 2024-03-12 Yifan Chen , Houman Owhadi , Florian Schäfer

In the gravitational-wave analysis of pulsar-timing-array datasets, parameter estimation is usually performed using Markov Chain Monte Carlo methods to explore posterior probability densities. We introduce an alternative procedure that…

General Relativity and Quantum Cosmology · Physics 2024-05-16 Michele Vallisneri , Marco Crisostomi , Aaron D. Johnson , Patrick M. Meyers

This paper presents a novel stochastic gradient descent algorithm for constrained optimization. The proposed algorithm randomly samples constraints and components of the finite sum objective function and relies on a relaxed logarithmic…

Optimization and Control · Mathematics 2025-05-13 Naum Dimitrieski , Jing Cao , Christian Ebenbauer

This paper explores numerical methods for solving a convex differentiable semi-infinite program. We introduce a primal-dual gradient method which performs three updates iteratively: a momentum gradient ascend step to update the constraint…

Optimization and Control · Mathematics 2024-07-23 Yao Yao , Qihang Lin , Tianbao Yang

We highlight a pitfall when applying stochastic variational inference to general Bayesian networks. For global random variables approximated by an exponential family distribution, natural gradient steps, commonly starting from a unit length…

Machine Learning · Statistics 2015-07-17 Ulrich Paquet

We address the generalized Nash equilibrium seeking problem in a partial-decision information scenario, where each agent can only exchange information with some neighbors, although its cost function possibly depends on the strategies of all…

Optimization and Control · Mathematics 2021-12-14 Mattia Bianchi , Giuseppe Belgioioso , Sergio Grammatico

Approximate Natural Gradient Descent (NGD) methods are an important family of optimisers for deep learning models, which use approximate Fisher information matrices to pre-condition gradients during training. The empirical Fisher (EF)…

Machine Learning · Computer Science 2024-11-07 Xiaodong Wu , Wenyi Yu , Chao Zhang , Philip Woodland

The Bayesian smoothing equations are generally intractable for systems described by nonlinear stochastic differential equations and discrete-time measurements. Gaussian approximations are a computationally efficient way to approximate the…

Dynamical Systems · Mathematics 2016-04-05 Juha Ala-Luhtala , Simo Särkkä , Robert Piché

Gaussian processes (GPs) have gained popularity as flexible machine learning models for regression and function approximation with an in-built method for uncertainty quantification. However, GPs suffer when the amount of training data is…

Machine Learning · Statistics 2025-11-26 Jonas Latz , Aretha L. Teckentrup , Simon Urbainczyk

It seems that in the current age, computers, computation, and data have an increasingly important role to play in scientific research and discovery. This is reflected in part by the rise of machine learning and artificial intelligence,…

Machine Learning · Computer Science 2024-05-15 Ronan Keane

A generic, fast and asymptotically efficient method for parametric estimation is described. It is based on the projected stochastic gradient descent on the log-likelihood function corrected by a single step of the Fisher scoring algorithm.…

Statistics Theory · Mathematics 2024-04-16 Alexandre Brouste , Youssef Esstafa

Minimax problems of the form $\min_x \max_y \Psi(x,y)$ have attracted increased interest largely due to advances in machine learning, in particular generative adversarial networks. These are typically trained using variants of stochastic…

Optimization and Control · Mathematics 2023-04-14 Radu Ioan Boţ , Axel Böhm

Many machine learning problems can be expressed as the optimization of some cost functional over a parametric family of probability distributions. It is often beneficial to solve such optimization problems using natural gradient methods.…

Machine Learning · Statistics 2020-02-14 Michael Arbel , Arthur Gretton , Wuchen Li , Guido Montufar

We present a method to approximate Gaussian process regression models for large datasets by considering only a subset of the data. Our approach is novel in that the size of the subset is selected on the fly during exact inference with…

Machine Learning · Computer Science 2023-05-01 Simon Bartels , Kristoffer Stensbo-Smidt , Pablo Moreno-Muñoz , Wouter Boomsma , Jes Frellsen , Søren Hauberg

In many applications involving large dataset or online updating, stochastic gradient descent (SGD) provides a scalable way to compute parameter estimates and has gained increasing popularity due to its numerical convenience and memory…

Machine Learning · Statistics 2017-07-04 Yixin Fang , Jinfeng Xu , Lei Yang
‹ Prev 1 8 9 10 Next ›