paper-with-me

Papers

Approximation of Lipschitz Functions using Deep Spline Neural Networks

2022-04-13 · Sebastian Neumayer, Alexis Goujon, Pakshal Bohra, Michael Unser

Lipschitz-constrained neural networks have many applications in machine learning. Since designing and training expressive Lipschitz-constrained networks is very challenging, there is a need for improved methods and a better theoretical understanding. Unfortunately, it turns out that ReLU networks have provable disadvantages in this setting. Hence, we propose to use learnable spline activation functions with at least 3 linear regions instead. We prove that this choice is optimal among all component-wise $1$-Lipschitz activation functions in the sense that no other weight constrained architecture can approximate a larger class of functions. Additionally, this choice is at least as expressive as the recently introduced non component-wise Groupsort activation function for spectral-norm-constrained weights. Previously published numerical results support our theoretical findings.

📄 PDF Abstract BibTeX arXiv:2204.06233

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

NON 설명 없음

Similar Papers 제목 키워드 기반

Learning Lipschitz-Controlled Activation Functions in Neural Networks for Plug-and-Play Image Reconstruction Methods

2021-10-19 · NeurIPS Workshop Deep_Invers 2021 12 · Pakshal Bohra, Alexis Goujon, Dimitris Perdios, Sébastien Emery 외

Ill-posed linear inverse problems are frequently encountered in image reconstruction tasks. Image reconstruction methods that combine the Plug-and-Play (PnP) priors framework with convolutional neural network (CNN) based…

DenoisingImage Reconstruction

Layer-wise Lipschitz-Product Control for Deep Kolmogorov--Arnold Network Representations of Compositionally Structured Functions

2026-04-29 · Aleksander Tankman arxiv

We prove that any continuous function f from [0,1]^n to R representable by a finite computation tree with N internal nodes and compositional sparsity s = O(1) admits a deep Kolmogorov-Arnold Network (KAN) representation.…

Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions

2022-10-28 · Stanislas Ducotterd, Alexis Goujon, Pakshal Bohra, Dimitris Perdios 외

Lipschitz-constrained neural networks have several advantages over unconstrained ones and can be applied to a variety of problems, making them a topic of attention in the deep learning community. Unfortunately, it has be…

Bi-Lipschitz Ansatz for Anti-Symmetric Functions

2025-03-06 · Nadav Dym, Jianfeng Lu, Matan Mizrachi

Motivated by applications for simulating quantum many body functions, we propose a new universal ansatz for approximating anti-symmetric functions. The main advantage of this ansatz over previous alternatives is that it …

Approximation theory for 1-Lipschitz ResNets

2025-05-17 · Davide Murari, Takashi Furuya, Carola-Bibiane Schönlieb

1-Lipschitz neural networks are fundamental for generative modelling, inverse problems, and robust classifiers. In this paper, we focus on 1-Lipschitz residual networks (ResNets) based on explicit Euler steps of negative…