English
Related papers

Related papers: On the Ideal Number of Groups for Isometric Gradie…

200 papers

This paper studies how neural network architecture affects the speed of training. We introduce a simple concept called gradient confusion to help formally analyze this. When gradient confusion is high, stochastic gradients produced by…

Machine Learning · Computer Science 2020-07-08 Karthik A. Sankararaman , Soham De , Zheng Xu , W. Ronny Huang , Tom Goldstein

The present paper deals with the data-driven design of regularizers in the form of artificial neural networks, for solving certain inverse problems formulated as optimal control problems. These regularizers aim at improving accuracy,…

Optimization and Control · Mathematics 2023-03-06 Sebastien Court

Gradient boosting is a state-of-the-art prediction technique that sequentially produces a model in the form of linear combinations of simple predictors---typically decision trees---by solving an infinite-dimensional convex optimization…

Statistics Theory · Mathematics 2017-07-18 Gérard Biau , Benoît Cadre

Natural gradient methods have been used to optimise the parameters of probability distributions in a variety of settings, often resulting in fast-converging procedures. Unfortunately, for many distributions of interest, computing the…

Machine Learning · Statistics 2024-05-28 Jonathan So , Richard E. Turner

This paper investigates multilevel initialization strategies for training very deep neural networks with a layer-parallel multigrid solver. The scheme is based on the continuous interpretation of the training problem as a problem of optimal…

Machine Learning · Computer Science 2019-12-20 Eric C. Cyr , Stefanie Günther , Jacob B. Schroder

Batch Normalization (BN) is a milestone technique in the development of deep learning, enabling various networks to train. However, normalizing along the batch dimension introduces problems --- BN's error increases rapidly when the batch…

Computer Vision and Pattern Recognition · Computer Science 2018-06-13 Yuxin Wu , Kaiming He

Gradient Descent (GD) and Conjugate Gradient (CG) methods are among the most effective iterative algorithms for solving unconstrained optimization problems, particularly in machine learning and statistical modeling, where they are employed…

Optimization and Control · Mathematics 2024-12-19 Xianqi Jiao , Jia Liu , Zhiping Chen

We study the effect of normalization on the layers of deep neural networks of feed-forward type. A given layer $i$ with $N_{i}$ hidden units is allowed to be normalized by $1/N_{i}^{\gamma_{i}}$ with $\gamma_{i}\in[1/2,1]$ and we study the…

Machine Learning · Computer Science 2022-09-05 Jiahui Yu , Konstantinos Spiliopoulos

Normalization of polynomials plays a vital role in the approximate basis computation of vanishing ideals. Coefficient normalization, which normalizes a polynomial with its coefficient norm, is the most common method in computer algebra.…

Symbolic Computation · Computer Science 2022-07-04 Hiroshi Kera

In recent years, deep learning has been connected with optimal control as a way to define a notion of a continuous underlying learning problem. In this view, neural networks can be interpreted as a discretization of a parametric Ordinary…

Optimization and Control · Mathematics 2020-07-07 Joubine Aghili , Olga Mula

As neural networks become deeper, the redundancy within their parameters increases. This phenomenon has led to several methods that attempt to reduce the correlation between convolutional filters. We propose a computationally efficient…

Computer Vision and Pattern Recognition · Computer Science 2024-02-20 Yoav Kurtz , Noga Bar , Raja Giryes

We propose a unified framework for neural net normalization, regularization and optimization, which includes Path-SGD and Batch-Normalization and interpolates between them across two different dimensions. Through this framework we…

Machine Learning · Computer Science 2016-01-20 Behnam Neyshabur , Ryota Tomioka , Ruslan Salakhutdinov , Nathan Srebro

This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapidly when presented with previously unseen tasks. Tasks are…

Machine Learning · Computer Science 2018-10-19 Amir Erfan Eshratifar , David Eigen , Massoud Pedram

Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications. Over-smoothing is one of the key issues which limit the performance…

Machine Learning · Computer Science 2020-06-15 Kaixiong Zhou , Xiao Huang , Yuening Li , Daochen Zha , Rui Chen , Xia Hu

A method for finding an optimum $n$-dimensional commutative group code of a given order $M$ is presented. The approach explores the structure of lattices related to these codes and provides a significant reduction in the number of…

Information Theory · Computer Science 2013-03-26 Cristiano Torezzan , João E. Strapasson , Sueli I. R. Costa , Rogerio M. Siqueira

Distributionally robust optimization (DRO) problems are increasingly seen as a viable method to train machine learning models for improved model generalization. These min-max formulations, however, are more difficult to solve. We therefore…

Machine Learning · Statistics 2020-11-03 Soumyadip Ghosh , Mark Squillante , Ebisa Wollega

Oscillator networks represent a promising technology for unconventional computing and artificial intelligence. Thus far, these systems have primarily been demonstrated in small-scale implementations, such as Ising Machines for solving…

Disordered Systems and Neural Networks · Physics 2025-04-17 Théophile Rageau , Julie Grollier

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock

The communication of gradients is costly for training deep neural networks with multiple devices in computer vision applications. In particular, the growing size of deep learning models leads to higher communication overheads that defy the…

Machine Learning · Computer Science 2020-02-26 An Xu , Zhouyuan Huo , Heng Huang

Maintaining numerical stability in machine learning models is crucial for their reliability and performance. One approach to maintain stability of a network layer is to integrate the condition number of the weight matrix as a regularizing…

Machine Learning · Computer Science 2024-10-02 Rossen Nenov , Daniel Haider , Peter Balazs