English
Related papers

Related papers: Efficient Numerical Algorithm for Large-Scale Damp…

200 papers

Natural Gradient Descent, a second-degree optimization method motivated by the information geometry, makes use of the Fisher Information Matrix instead of the Hessian which is typically used. However, in many cases, the Fisher Information…

Machine Learning · Computer Science 2023-03-10 Rajesh Shrestha

Natural-gradient descent (NGD) on structured parameter spaces (e.g., low-rank covariances) is computationally challenging due to difficult Fisher-matrix computations. We address this issue by using \emph{local-parameter coordinates} to…

Machine Learning · Statistics 2022-01-19 Wu Lin , Frank Nielsen , Mohammad Emtiyaz Khan , Mark Schmidt

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

Natural gradient descent is an optimization method traditionally motivated from the perspective of information geometry, and works well for many applications as an alternative to stochastic gradient descent. In this paper we critically…

Machine Learning · Computer Science 2020-09-22 James Martens

Latent variable models are powerful tools for modeling complex phenomena involving in particular partially observed data, unobserved variables or underlying complex unknown structures. Inference is often difficult due to the latent…

Statistics Theory · Mathematics 2023-06-23 Charlotte Baey , Maud Delattre , Estelle Kuhn , Jean-Benoist Leger , Sarah Lemler

We develop several efficient algorithms for the classical \emph{Matrix Scaling} problem, which is used in many diverse areas, from preconditioning linear systems to approximation of the permanent. On an input $n\times n$ matrix $A$, this…

Data Structures and Algorithms · Computer Science 2017-04-10 Zeyuan Allen-Zhu , Yuanzhi Li , Rafael Oliveira , Avi Wigderson

We propose efficient numerical schemes for implementing the natural gradient descent (NGD) for a broad range of metric spaces with applications to PDE-based optimization problems. Our technique represents the natural gradient direction as a…

Optimization and Control · Mathematics 2023-01-12 Levon Nurbekyan , Wanzhou Lei , Yunan Yang

The paper looks at a scaled variant of the stochastic gradient descent algorithm for the matrix completion problem. Specifically, we propose a novel matrix-scaling of the partial derivatives that acts as an efficient preconditioning for the…

Machine Learning · Computer Science 2016-10-06 Bamdev Mishra , Rodolphe Sepulchre

Natural gradient descent (NGD) provided deep insights and powerful tools to deep neural networks. However the computation of Fisher information matrix becomes more and more difficult as the network structure turns large and complex. This…

Machine Learning · Computer Science 2021-09-22 Weihua Liu , Xiabi Liu

Natural gradient descent, which preconditions a gradient descent update with the Fisher information matrix of the underlying statistical model, is a way to capture partial second-order information. Several highly visible works have…

Machine Learning · Computer Science 2020-06-09 Frederik Kunstner , Lukas Balles , Philipp Hennig

The Cholesky decomposition is a fundamental tool for solving linear systems with symmetric and positive definite matrices which are ubiquitous in linear algebra, optimization, and machine learning. Its numerical stability can be improved by…

Machine Learning · Computer Science 2025-07-29 Filip de Roos , Fabio Muratore

Natural gradients can improve convergence in stochastic variational inference significantly but inverting the Fisher information matrix is daunting in high dimensions. Moreover, in Gaussian variational approximation, natural gradient…

Computation · Statistics 2025-02-05 Linda S. L. Tan

A new algorithm to approximate Hermitian matrices by positive semidefinite Hermitian matrices based on modified Cholesky decompositions is presented. In contrast to existing algorithms, this algorithm allows to specify bounds on the…

Numerical Analysis · Mathematics 2019-12-12 Joscha Reimer

In this work, we propose Natural Hypergradient Descent (NHGD), a new method for solving bilevel optimization problems. To address the computational bottleneck in hypergradient estimation--namely, the need to compute or approximate Hessian…

Machine Learning · Computer Science 2026-04-02 Deyi Kong , Zaiwei Chen , Shuzhong Zhang , Shancong Mou

The modified Cholesky decomposition is commonly used for precision matrix estimation given a specified order of random variables. However, the order of variables is often not available or cannot be pre-determined. In this work, we propose…

Machine Learning · Statistics 2021-11-23 Xiaoning Kang , Xinwei Deng

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

We present practical Levenberg-Marquardt variants of Gauss-Newton and natural gradient methods for solving non-convex optimization problems that arise in training deep neural networks involving enormous numbers of variables and huge data…

Machine Learning · Computer Science 2019-06-07 Yi Ren , Donald Goldfarb

This paper studies the estimation of a large covariance matrix. We introduce a novel procedure called ChoSelect based on the Cholesky factor of the inverse covariance. This method uses a dimension reduction strategy by selecting the pattern…

Statistics Theory · Mathematics 2010-10-13 Nicolas Verzelen

In this paper, we propose a scalable algorithm for spectral embedding. The latter is a standard tool for graph clustering. However, its computational bottleneck is the eigendecomposition of the graph Laplacian matrix, which prevents its…

Machine Learning · Computer Science 2019-04-12 Mireille El Gheche , Giovanni Chierchia , Pascal Frossard

Bilevel hyperparameter optimization has received growing attention thanks to the fast development of machine learning. Due to the tremendous size of data sets, the scale of bilevel hyperparameter optimization problem could be extremely…

Optimization and Control · Mathematics 2025-10-27 Yixin Wang , Qingna Li , Liwei Zhang
‹ Prev 1 2 3 10 Next ›