paper-with-me

홈 › Papers

Universal Lipschitz Approximation in Bounded Depth Neural Networks

2019-04-09 · Jeremy E. J. Cohen, Todd Huster, Ra Cohen

Adversarial attacks against machine learning models are a rather hefty obstacle to our increasing reliance on these models. Due to this, provably robust (certified) machine learning models are a major topic of interest. Lipschitz continuous models present a promising approach to solving this problem. By leveraging the expressive power of a variant of neural networks which maintain low Lipschitz constants, we prove that three layer neural networks using the FullSort activation function are Universal Lipschitz function Approximators (ULAs). This both explains experimental results and paves the way for the creation of better certified models going forward. We conclude by presenting experimental results that suggest that ULAs are a not just a novelty, but a competitive approach to providing certified classifiers, using these results to motivate several potential topics of further research.

📄 PDF Abstract BibTeX arXiv:1904.04861

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Minimum Width for Universal Approximation

2020-06-16 · ICLR 2021 1 · Sejun Park, Chulhee Yun, Jaeho Lee, Jinwoo Shin

The universal approximation property of width-bounded networks has been studied as a dual of classical universal approximation results on depth-bounded networks. However, the critical width enabling the universal approxi…

Arbitrary-Depth Universal Approximation Theorems for Operator Neural Networks

2021-09-23 · Annan Yu, Chloé Becquey, Diana Halikias, Matthew Esmaili Mallory 외

The standard Universal Approximation Theorem for operator neural networks (NNs) holds for arbitrary width and bounded depth. Here, we prove that operator NNs of bounded width and arbitrary depth are universal approximato…

2k

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…

On Explicit Super-Expressive Approximation for Neural Networks

2026-07-07 · Feng-Lei Fan, Ze-Yu Li, Chen-Yu Wang, Jian-Jun Wang arxiv

In this work, we investigate the fixed-architecture neural network approximation with explicit parameter bounds and elementary activations. While prior work demonstrated super-expressive approximation using fixed-size ne…

Optimal Approximation Rate of ReLU Networks in terms of Width and Depth

2021-02-28 · Zuowei Shen, Haizhao Yang, Shijun Zhang

This paper concentrates on the approximation power of deep feed-forward neural networks in terms of width and depth. It is proved by construction that ReLU networks with width $\mathcal{O}\big(\max\{d\lfloor N^{1/d}\rflo…