English
Related papers

Related papers: Tensor Programs VI: Feature Learning in Infinite-D…

200 papers

Feature propagation in Deep Neural Networks (DNNs) can be associated to nonlinear discrete dynamical systems. The novelty, in this paper, lies in letting the discretization parameter (time step-size) vary from layer to layer, which needs to…

Optimization and Control · Mathematics 2022-04-20 Harbir Antil , Hugo Díaz , Evelyn Herberg

Deep learning has been successful in automating the design of features in machine learning pipelines. However, the algorithms optimizing neural network parameters remain largely hand-designed and computationally inefficient. We study if we…

Machine Learning · Computer Science 2021-10-26 Boris Knyazev , Michal Drozdzal , Graham W. Taylor , Adriana Romero-Soriano

The growing scale of deep learning models has rendered standard hyperparameter (HP) optimization prohibitively expensive. A promising solution is the use of scale-aware hyperparameters, which can enable direct transfer of optimal HPs from…

Machine Learning · Computer Science 2025-12-30 Nikhil Ghosh , Denny Wu , Alberto Bietti

Neural network (NN) designed for challenging machine learning tasks is in general a highly nonlinear mapping that contains massive variational parameters. High complexity of NN, if unbounded or unconstrained, might unpredictably cause…

Machine Learning · Computer Science 2025-05-23 Yong Qing , Ke Li , Peng-Fei Zhou , Shi-Ju Ran

The empirical emergence of neural collapse -- a surprising symmetry in the feature representations of the training data in the penultimate layer of deep neural networks -- has spurred a line of theoretical research aimed at its…

Machine Learning · Computer Science 2025-05-22 Peter Súkeník , Christoph H. Lampert , Marco Mondelli

We study the generalization of over-parameterized deep networks (for image classification) in relation to the convex hull of their training sets. Despite their great success, generalization of deep networks is considered a mystery. These…

Machine Learning · Computer Science 2022-03-22 Roozbeh Yousefzadeh

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

Residual units are wildly used for alleviating optimization difficulties when building deep neural networks. However, the performance gain does not well compensate the model size increase, indicating low parameter efficiency in these…

Computer Vision and Pattern Recognition · Computer Science 2017-03-16 Chen Yunpeng , Jin Xiaojie , Kang Bingyi , Feng Jiashi , Yan Shuicheng

Tensor Networks (TN) offer a powerful framework to efficiently represent very high-dimensional objects. TN have recently shown their potential for machine learning applications and offer a unifying view of common tensor decomposition models…

Machine Learning · Computer Science 2021-06-24 Meraj Hashemizadeh , Michelle Liu , Jacob Miller , Guillaume Rabusseau

Yang (2020a) recently showed that the Neural Tangent Kernel (NTK) at initialization has an infinite-width limit for a large class of architectures including modern staples such as ResNet and Transformers. However, their analysis does not…

Machine Learning · Computer Science 2021-05-11 Greg Yang , Etai Littwin

We present a fully constructive analysis of deep ReLU neural networks for classification and function approximation tasks. First, we prove that any dataset with $N$ distinct points in $\mathbb{R}^d$ and $M$ output classes can be exactly…

Machine Learning · Statistics 2025-06-25 Martín Hernández , Enrique Zuazua

Deep neural networks (NNs) encounter scalability limitations when confronted with a vast array of neurons, thereby constraining their achievable network depth. To address this challenge, we propose an integration of tensor networks (TN)…

Disordered Systems and Neural Networks · Physics 2024-08-20 Saeed S. Jahromi , Roman Orus

Hypernetworks, neural networks that predict the parameters of another neural network, are powerful models that have been successfully used in diverse applications from image generation to multi-task learning. Unfortunately, existing…

Machine Learning · Computer Science 2023-06-30 Jose Javier Gonzalez Ortiz , John Guttag , Adrian Dalca

Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications. We introduce BlockDrop, an approach that learns to dynamically choose which…

Computer Vision and Pattern Recognition · Computer Science 2019-01-29 Zuxuan Wu , Tushar Nagarajan , Abhishek Kumar , Steven Rennie , Larry S. Davis , Kristen Grauman , Rogerio Feris

We develop a fast end-to-end method for training lightweight neural networks using multiple classifier heads. By allowing the model to determine the importance of each head and rewarding the choice of a single shallow classifier, we are…

Machine Learning · Computer Science 2020-04-20 Bartosz Wójcik , Maciej Wołczyk , Klaudia Bałazy , Jacek Tabor

Deep neural networks are powerful tools for solving nonlinear problems in science and engineering, but training highly accurate models becomes challenging as problem complexity increases. Non-convex optimization and sensitivity to…

Machine Learning · Computer Science 2026-04-20 Ethan Mulle , Wei Kang , Qi Gong

The performance of deep neural networks (DNN) is very sensitive to the particular choice of hyper-parameters. To make it worse, the shape of the learning curve can be significantly affected when a technique like batchnorm is used. As a…

Machine Learning · Computer Science 2019-05-24 Hyunghun Cho , Yongjin Kim , Eunjung Lee , Daeyoung Choi , Yongjae Lee , Wonjong Rhee

The possibility for one to recover the parameters-weights and biases-of a neural network thanks to the knowledge of its function on a subset of the input space can be, depending on the situation, a curse or a blessing. On one hand,…

Statistics Theory · Mathematics 2023-05-15 Joachim Bona-Pellissier , François Bachoc , François Malgouyres

Overparametrization is a key factor in the absence of convexity to explain global convergence of gradient descent (GD) for neural networks. Beside the well studied lazy regime, infinite width (mean field) analysis has been developed for…

Neural and Evolutionary Computing · Computer Science 2023-02-07 Raphaël Barboni , Gabriel Peyré , François-Xavier Vialard

We study the convergence of gradient flow for the training of deep neural networks. If Residual Neural Networks are a popular example of very deep architectures, their training constitutes a challenging optimization problem due notably to…

Machine Learning · Computer Science 2025-07-22 Raphaël Barboni , Gabriel Peyré , François-Xavier Vialard