English
Related papers

Related papers: A Rescaling-Invariant Lipschitz Bound Based on Pat…

200 papers

We propose a non-parametric variant of binary regression, where the hypothesis is regularized to be a Lipschitz function taking a metric space to [0,1] and the loss is logarithmic. This setting presents novel computational and statistical…

Machine Learning · Computer Science 2020-10-21 Ariel Avital , Klim Efremenko , Aryeh Kontorovich , David Toplin , Bo Waggoner

We study the memorization power of feedforward ReLU neural networks. We show that such networks can memorize any $N$ points that satisfy a mild separability assumption using $\tilde{O}\left(\sqrt{N}\right)$ parameters. Known VC-dimension…

Machine Learning · Computer Science 2021-10-08 Gal Vardi , Gilad Yehudai , Ohad Shamir

In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness. The proof of generalization does not overcome the…

Machine Learning · Computer Science 2019-09-13 Chris Finlay , Jeff Calder , Bilal Abbasi , Adam Oberman

Network pruning reduces the size of neural networks by removing (pruning) neurons such that the performance drop is minimal. Traditional pruning approaches focus on designing metrics to quantify the usefulness of a neuron which is often…

Computer Vision and Pattern Recognition · Computer Science 2021-11-01 Shehryar Malik , Muhammad Umair Haider , Omer Iqbal , Murtaza Taj

In this paper, we consider one dimensional (shallow) ReLU neural networks in which weights are chosen randomly and only the terminal layer is trained. First, we mathematically show that for such networks L2-regularized regression…

Machine Learning · Computer Science 2023-10-05 Jakob Heiss , Josef Teichmann , Hanna Wutte

It is well-known that standard neural networks, even with a high classification accuracy, are vulnerable to small $\ell_\infty$-norm bounded adversarial perturbations. Although many attempts have been made, most previous works either can…

Machine Learning · Computer Science 2021-06-15 Bohang Zhang , Tianle Cai , Zhou Lu , Di He , Liwei Wang

Understanding the properties of the parameter space in feed-forward ReLU networks is critical for effectively analyzing and guiding training dynamics. After initialization, training under gradient flow decisively restricts the parameter…

Machine Learning · Computer Science 2026-02-03 Marco Nurisso , Pierrick Leroy , Giovanni Petri , Francesco Vaccarino

The cost of hyperparameter tuning in deep learning has been rising with model sizes, prompting practitioners to find new tuning methods using a proxy of smaller networks. One such proposal uses $\mu$P parameterized networks, where the…

Machine Learning · Statistics 2023-12-11 Blake Bordelon , Lorenzo Noci , Mufan Bill Li , Boris Hanin , Cengiz Pehlevan

This paper studies the approximation capacity of ReLU neural networks with norm constraint on the weights. We prove upper and lower bounds on the approximation error of these networks for smooth function classes. The lower bound is derived…

Machine Learning · Computer Science 2023-03-31 Yuling Jiao , Yang Wang , Yunfei Yang

A Random Vector Functional Link (RVFL) network is a depth-2 neural network with random inner weights and biases. Only the outer weights of such an architecture are to be learned, so the learning process boils down to a linear optimization…

Machine Learning · Statistics 2025-06-26 Palina Salanevich , Olov Schavemaker

Feature maps associated with positive definite kernels play a central role in kernel methods and learning theory, where regularity properties such as Lipschitz continuity are closely related to robustness and stability guarantees. Despite…

Machine Learning · Statistics 2026-04-06 Justin Reverdi , Sixin Zhang , Fabrice Gamboa , Serge Gratton

Despite existing work on ensuring generalization of neural networks in terms of scale sensitive complexity measures, such as norms, margin and sharpness, these complexity measures do not offer an explanation of why neural networks…

Machine Learning · Computer Science 2018-05-31 Behnam Neyshabur , Zhiyuan Li , Srinadh Bhojanapalli , Yann LeCun , Nathan Srebro

Deep Learning models have become the dominant approach in several areas due to their high performance. Unfortunately, the size and hence computational requirements of operating such models can be considerably high. Therefore, this…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Abdullah Salama , Oleksiy Ostapenko , Tassilo Klein , Moin Nabi

Rectified Linear Units (ReLU) have become the main model for the neural units in current deep learning systems. This choice has been originally suggested as a way to compensate for the so called vanishing gradient problem which can undercut…

Disordered Systems and Neural Networks · Physics 2024-05-06 Carlo Baldassi , Enrico M. Malatesta , Riccardo Zecchina

We prove that overparametrized neural networks are able to generalize with a test error that is independent of the level of overparametrization, and independent of the Vapnik-Chervonenkis (VC) dimension. We prove explicit bounds that only…

Machine Learning · Computer Science 2026-01-27 Anandatheertha Bapu , Thomas Chen , Chun-Kai Kevin Chien , Patricia Muñoz Ewald , Andrew G. Moore

The Lipschitz bound, a technique from robust statistics, can limit the maximum changes in the output concerning the input, taking into account associated irrelevant biased factors. It is an efficient and provable method for examining the…

Machine Learning · Computer Science 2023-12-13 Yaning Jia , Chunhui Zhang

Deep learning has achieved remarkable success across a wide range of domains, significantly expanding the frontiers of what is achievable in artificial intelligence. Yet, despite these advances, critical challenges remain -- most notably,…

Machine Learning · Computer Science 2026-02-05 Róisín Luo

We prove an exponential size separation between depth 2 and depth 3 neural networks (with real inputs), when approximating a $\mathcal{O}(1)$-Lipschitz target function to constant accuracy, with respect to a distribution with support in the…

Machine Learning · Computer Science 2024-11-08 Itay Safran , Daniel Reichman , Paul Valiant

We explore the ability of overparameterized shallow ReLU neural networks to learn Lipschitz, nondifferentiable, bounded functions with additive noise when trained by Gradient Descent (GD). To avoid the problem that in the presence of noise,…

Machine Learning · Computer Science 2023-04-07 Ilja Kuzborskij , Csaba Szepesvári

Deep neural networks achieve state-of-the-art results on several tasks while increasing in complexity. It has been shown that neural networks can be pruned during training by imposing sparsity inducing regularizers. In this paper, we…

Machine Learning · Statistics 2019-08-12 Chaithanya Kumar Mummadi , Tim Genewein , Dan Zhang , Thomas Brox , Volker Fischer