English
Related papers

Related papers: Relative gradient optimization of the Jacobian ter…

200 papers

Deep learning networks generally use non-biological learning methods. By contrast, networks based on more biologically plausible learning, such as Hebbian learning, show comparatively poor performance and difficulties of implementation.…

Neural and Evolutionary Computing · Computer Science 2021-11-02 Thomas Miconi

Natural gradient descent has proven effective at mitigating the effects of pathological curvature in neural network optimization, but little is known theoretically about its convergence properties, especially for \emph{nonlinear} networks.…

Machine Learning · Statistics 2019-10-29 Guodong Zhang , James Martens , Roger Grosse

Accounting for the uncertainty in the predictions of modern neural networks is a challenging and important task in many domains. Existing algorithms for uncertainty estimation require modifying the model architecture and training procedure…

Machine Learning · Statistics 2022-05-09 Alexander Fishkov , Maxim Panov

This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network, enabling training and evaluating over heterogeneous collections of meshes that do not share a…

Graphics · Computer Science 2022-05-09 Noam Aigerman , Kunal Gupta , Vladimir G. Kim , Siddhartha Chaudhuri , Jun Saito , Thibault Groueix

We introduce a novel method to compute a rank $m$ approximation of the inverse of the Hessian matrix in the distributed regime. By leveraging the differences in gradients and parameters of multiple Workers, we are able to efficiently…

Machine Learning · Computer Science 2017-09-18 Sébastien M. R. Arnold , Chunming Wang

We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation. Typically, enforcing invertibility requires partitioning dimensions or restricting…

Machine Learning · Computer Science 2019-05-21 Jens Behrmann , Will Grathwohl , Ricky T. Q. Chen , David Duvenaud , Jörn-Henrik Jacobsen

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

Machine Learning · Computer Science 2024-03-13 Soo Min Kwon , Zekai Zhang , Dogyoon Song , Laura Balzano , Qing Qu

Derivative training is an established method that can significantly increase the accuracy of neural networks in certain low-dimensional tasks. In this paper, we extend this improvement to an illustrative image analysis problem:…

Machine Learning · Computer Science 2025-02-04 Vsevolod I. Avrutskiy

With the tremendous success of deep learning in visual tasks, the representations extracted from intermediate layers of learned models, that is, deep features, attract much attention of researchers. Previous empirical analysis shows that…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Qi Qian , Juhua Hu , Hao Li

Neural networks are predominantly trained using gradient-based methods, yet in many applications their final predictions remain far from the accuracy attainable within the model's expressive capacity. We introduce Linearized Subspace…

Machine Learning · Computer Science 2026-01-21 Wenbo Cao , Weiwei Zhang

An effective numerical method is presented for optimizing model parameters that can be applied to any type of system of non-linear equations and any number of data-points, which does not require explicit formulation of the objective…

Numerical Analysis · Mathematics 2022-03-09 M. H. A. Piro , J. S. Bell , M. Poschmann , A. Prudil , P. Chan

Powerful deep neural networks are vulnerable to adversarial attacks. To obtain adversarially robust models, researchers have separately developed adversarial training and Jacobian regularization techniques. There are abundant theoretical…

Machine Learning · Statistics 2024-12-18 Dongya Wu , Xin Li

Data augmentation is essential to achieve state-of-the-art performance in many deep learning applications. However, the most effective augmentation techniques become computationally prohibitive for even medium-sized datasets. To address…

Machine Learning · Computer Science 2023-07-21 Tian Yu Liu , Baharan Mirzasoleiman

A promising trend in deep learning replaces traditional feedforward networks with implicit networks. Unlike traditional networks, implicit networks solve a fixed point equation to compute inferences. Solving for the fixed point varies in…

Machine Learning · Computer Science 2021-12-28 Samy Wu Fung , Howard Heaton , Qiuwei Li , Daniel McKenzie , Stanley Osher , Wotao Yin

In machine learning, there is a fundamental trade-off between ease of optimization and expressive power. Neural Networks, in particular, have enormous expressive power and yet are notoriously challenging to train. The nature of that…

Machine Learning · Computer Science 2015-11-24 Diogo Almeida , Nate Sauder

Deep learning optimization exhibits structure that is not captured by worst-case gradient bounds. Empirically, gradients along training trajectories are often temporally predictable and evolve within a low-dimensional subspace. In this work…

Machine Learning · Computer Science 2026-01-09 Anherutowa Calvo

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

Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions. This issue of deep neural networks has led to a number of…

Machine Learning · Computer Science 2022-02-22 Ming-Chang Chiu , Xuezhe Ma

Distributed machine learning has recently become a critical paradigm for training large models on vast datasets. We examine the stochastic optimization problem for deep learning within synchronous parallel computing environments under…

Machine Learning · Computer Science 2024-11-07 Yoni Choukroun , Shlomi Azoulay , Pavel Kisilev

In machine learning, error back-propagation in multi-layer neural networks (deep learning) has been impressively successful in supervised and reinforcement learning tasks. As a model for learning in the brain, however, deep learning has…

Machine Learning · Computer Science 2016-12-19 Thomas Mesnard , Wulfram Gerstner , Johanni Brea