English
Related papers

Related papers: Sorting out Lipschitz function approximation

200 papers

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

Applications of optimal transport have recently gained remarkable attention thanks to the computational advantages of entropic regularization. However, in most situations the Sinkhorn approximation of the Wasserstein distance is replaced by…

Machine Learning · Statistics 2019-06-04 Giulia Luise , Alessandro Rudi , Massimiliano Pontil , Carlo Ciliberto

The universal approximation property uniformly with respect to weakly compact families of measures is established for several classes of neural networks. To that end, we prove that these neural networks are dense in Orlicz spaces, thereby…

Machine Learning · Statistics 2025-10-13 Mihriban Ceylan , David J. Prömel

We present PSiLON Net, an MLP architecture that uses $L_1$ weight normalization for each weight vector and shares the length parameter across the layer. The 1-path-norm provides a bound for the Lipschitz constant of a neural network and…

Machine Learning · Computer Science 2024-05-01 Aditya Biswas

Following the development of weighted asymptotic approximation properties of matrices, we introduce the analogous uniform approximation properties (that is, study the improvability of Dirichlet's Theorem). An added feature is the use of…

Number Theory · Mathematics 2022-02-25 Dmitry Kleinbock , Anurag Rao

Deep residual networks (ResNets) have demonstrated outstanding success in computer vision tasks, attributed to their ability to maintain gradient flow through deep architectures. Simultaneously, controlling the Lipschitz bound in neural…

Machine Learning · Computer Science 2025-03-03 Marius F. R. Juston , William R. Norris , Dustin Nottage , Ahmet Soylemezoglu

We prove linear convergence of gradient descent to a global optimum for the training of deep residual networks with constant layer width and smooth activation function. We show that if the trained weights, as a function of the layer index,…

Machine Learning · Computer Science 2023-01-26 Rama Cont , Alain Rossier , RenYuan Xu

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks. Existing methods are devoted to developing various robust training strategies or regularizations to update the weights of the neural network. But beyond the weights, the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Minjing Dong , Yanxi Li , Yunhe Wang , Chang Xu

Robustness with respect to weight perturbations underpins guarantees for generalization, pruning and quantization. Existing guarantees rely on Lipschitz bounds in parameter space, cover only plain feed-forward MLPs, and break under the…

Machine Learning · Computer Science 2025-06-16 Antoine Gonon , Nicolas Brisebarre , Elisa Riccietti , Rémi Gribonval

We initiate the study of the inherent tradeoffs between the size of a neural network and its robustness, as measured by its Lipschitz constant. We make a precise conjecture that, for any Lipschitz activation function and for most datasets,…

Machine Learning · Computer Science 2020-11-26 Sébastien Bubeck , Yuanzhi Li , Dheeraj Nagaraj

We propose a stable method to train Wasserstein generative adversarial networks. In order to enhance stability, we consider two objective functions using the $c$-transform based on Kantorovich duality which arises in the theory of optimal…

Machine Learning · Computer Science 2021-10-28 Dohyun Kwon , Yeoneung Kim , Guido Montúfar , Insoon Yang

The proximal algorithm is a powerful tool to minimize nonlinear and nonsmooth functionals in a general metric space. Motivated by the recent progress in studying the training dynamics of the noisy gradient descent algorithm on two-layer…

Optimization and Control · Mathematics 2026-05-19 Shuailong Zhu , Xiaohui Chen

We give a simple proof for the global convergence of gradient descent in training deep ReLU networks with the standard square loss, and show some of its improvements over the state-of-the-art. In particular, while prior works require all…

Machine Learning · Computer Science 2021-06-14 Quynh Nguyen

Graph Neural Networks (GNNs) are a broad class of connectionist models for graph processing. Recent studies have shown that GNNs can approximate any function on graphs, modulo the equivalence relation on graphs defined by the…

Machine Learning · Computer Science 2024-08-21 Giuseppe Alessio D'Inverno , Monica Bianchini , Maria Lucia Sampoli , Franco Scarselli

Tight estimation of the Lipschitz constant for deep neural networks (DNNs) is useful in many applications ranging from robustness certification of classifiers to stability analysis of closed-loop systems with reinforcement learning…

Machine Learning · Computer Science 2023-01-18 Mahyar Fazlyab , Alexander Robey , Hamed Hassani , Manfred Morari , George J. Pappas

Deep neural networks are notorious for being sensitive to small well-chosen perturbations, and estimating the regularity of such architectures is of utmost importance for safe and robust practical applications. In this paper, we investigate…

Machine Learning · Statistics 2019-10-28 Kevin Scaman , Aladin Virmaux

This paper studies the approximation capacity of neural networks with an arbitrary activation function and with norm constraint on the weights. Upper and lower bounds on the approximation error of these networks are computed for smooth…

Numerical Analysis · Mathematics 2025-12-24 Francesco Paolo Maiale , Anastasiia Trofimova , Arturo De Marinis

The convergence theory for the gradient sampling algorithm is extended to directionally Lipschitz functions. Although directionally Lipschitz functions are not necessarily locally Lipschitz, they are almost everywhere differentiable and…

Optimization and Control · Mathematics 2021-07-13 James V. Burke , Qiuying Lin

Decentralized optimization has become a fundamental tool for large-scale learning systems; however, most existing methods rely on the classical Lipschitz smoothness assumption, which is often violated in problems with rapidly varying…

Optimization and Control · Mathematics 2026-01-08 Yanan Bo , Yongqiang Wang

It is well known that the generative adversarial nets (GANs) are remarkably difficult to train. The recently proposed Wasserstein GAN (WGAN) creates principled research directions towards addressing these issues. But we found in practice…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Lijun Zhang , Yujin Zhang , Yongbin Gao