English
Related papers

Related papers: Natural Gradient Methods: Perspectives, Efficient-…

200 papers

Gradient regularization (GR) has been shown to improve the generalizability of trained models. While Natural Gradient Descent has been shown to accelerate optimization in the initial phase of training, little attention has been paid to how…

Machine Learning · Computer Science 2026-03-27 Satya Prakash Dash , Hossein Abdi , Wei Pan , Samuel Kaski , Mingfei Sun

In gradient descent, changing how we parametrize the model can lead to drastically different optimization trajectories, giving rise to a surprising range of meaningful inductive biases: identifying sparse classifiers or reconstructing…

Machine Learning · Statistics 2021-11-24 Anna Kerekes , Anna Mészáros , Ferenc Huszár

An open question in the Deep Learning community is why neural networks trained with Gradient Descent generalize well on real datasets even though they are capable of fitting random data. We propose an approach to answering this question…

Machine Learning · Computer Science 2020-02-26 Satrajit Chatterjee

Stochastic gradient descent (SGD), which dates back to the 1950s, is one of the most popular and effective approaches for performing stochastic optimization. Research on SGD resurged recently in machine learning for optimizing convex loss…

Machine Learning · Computer Science 2019-12-24 Jie Chen , Ronny Luss

Kakade's natural policy gradient method has been studied extensively in recent years, showing linear convergence with and without regularization. We study another natural gradient method based on the Fisher information matrix of the…

Optimization and Control · Mathematics 2025-02-05 Johannes Müller , Semih Çaycı , Guido Montúfar

Stochastic gradients for deep neural networks exhibit strong correlations along the optimization trajectory, and are often aligned with a small set of Hessian eigenvectors associated with outlier eigenvalues. Recent work shows that…

Machine Learning · Computer Science 2026-02-04 Julien Nicolas , Mohamed Maouche , Sonia Ben Mokhtar , Mark Coates

The natural gradient method has been used effectively in conjugate Gaussian process models, but the non-conjugate case has been largely unexplored. We examine how natural gradients can be used in non-conjugate stochastic settings, together…

Machine Learning · Statistics 2018-03-28 Hugh Salimbeni , Stefanos Eleftheriadis , James Hensman

Popular Bayes filters often apply linearization techniques, such as Taylor expansion or stochastic linear regression, to enable the use of the Kalman filter structure, but this can lead to large errors in strongly nonlinear systems. The…

Systems and Control · Electrical Eng. & Systems 2026-04-14 Tianyi Zhang , Wenhan Cao , Shengbo Eben Li

This report investigates the fitting of the Hessian or its inverse for stochastic optimizations using a Hessian fitting criterion derived from the preconditioned stochastic gradient descent (PSGD) method. This criterion is closely related…

Machine Learning · Statistics 2025-12-02 Xi-Lin Li

First order methods, which solely rely on gradient information, are commonly used in diverse machine learning (ML) and data analysis (DA) applications. This is attributed to the simplicity of their implementations, as well as low…

Machine Learning · Computer Science 2018-03-06 Sudhir B. Kylasa , Farbod Roosta-Khorasani , Michael W. Mahoney , Ananth Grama

A quantum generalization of Natural Gradient Descent is presented as part of a general-purpose optimization framework for variational quantum circuits. The optimization dynamics is interpreted as moving in the steepest descent direction…

Quantum Physics · Physics 2020-05-27 James Stokes , Josh Izaac , Nathan Killoran , Giuseppe Carleo

Stochastic gradient methods enable learning probabilistic models from large amounts of data. While large step-sizes (learning rates) have shown to be best for least-squares (e.g., Gaussian noise) once combined with parameter averaging,…

Machine Learning · Statistics 2018-11-22 Dmitry Babichev , Francis Bach

Many structured data-fitting applications require the solution of an optimization problem involving a sum over a potentially large number of measurements. Incremental gradient algorithms offer inexpensive iterations by sampling a subset of…

Numerical Analysis · Computer Science 2018-08-23 Michael P. Friedlander , Mark Schmidt

Practical Bayes filters often assume the state distribution of each time step to be Gaussian for computational tractability, resulting in the so-called Gaussian filters. When facing nonlinear systems, Gaussian filters such as extended…

Systems and Control · Electrical Eng. & Systems 2026-03-17 Wenhan Cao , Tianyi Zhang , Zeju Sun , Chang Liu , Stephen S. -T. Yau , Shengbo Eben Li

In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero training error so that thetraining algorithm induces an…

Machine Learning · Computer Science 2023-08-22 Hung-Hsu Chou , Carsten Gieshoff , Johannes Maly , Holger Rauhut

In this paper, we develop an efficient sketchy empirical natural gradient method (SENG) for large-scale deep learning problems. The empirical Fisher information matrix is usually low-rank since the sampling is only practical on a small…

Optimization and Control · Mathematics 2021-03-26 Minghan Yang , Dong Xu , Zaiwen Wen , Mengyun Chen , Pengxiang Xu

Estimating the Hessian matrix, especially for neural network training, is a challenging problem due to high dimensionality and cost. In this work, we compare the classical Sherman-Morrison update used in the popular BFGS method…

Machine Learning · Computer Science 2025-12-09 Adrian Przybysz , Mikołaj Kołek , Franciszek Sobota , Jarek Duda

Dual descent methods are commonly used to solve network optimization problems because their implementation can be distributed through the network. However, their convergence rates are typically very slow. This paper introduces a family of…

Optimization and Control · Mathematics 2011-04-07 M. Zargham , A. Ribeiro , A. Jadbabaie , A. Ozdaglar

Inspired by Gauss-Newton-like methods, we study the benefit of leveraging the structure of deep learning objectives, namely, the composition of a convex loss function and of a nonlinear network, in order to derive better direction oracles…

Machine Learning · Computer Science 2023-10-30 Vincent Roulet , Mathieu Blondel

Incorporating second order curvature information in gradient based methods have shown to improve convergence drastically despite its computational intensity. In this paper, we propose a stochastic (online) quasi-Newton method with…

Machine Learning · Computer Science 2020-10-16 S. Indrapriyadarsini , Shahrzad Mahboubi , Hiroshi Ninomiya , Hideki Asai