中文
相关论文

相关论文: A law of robustness for two-layers neural networks

200 篇论文

Robustness of deep neural networks against adversarial perturbations is a pressing concern motivated by recent findings showing the pervasive nature of such vulnerabilities. One method of characterizing the robustness of a neural network…

机器学习 · 统计学 2021-03-15 Hisham Husain , Borja Balle

We study the robust interpolation problem of arbitrary data distributions supported on a bounded space and propose a two-fold law of robustness. Robust interpolation refers to the problem of interpolating $n$ noisy training data points in…

机器学习 · 计算机科学 2023-06-02 Yihan Wu , Heng Huang , Hongyang Zhang

A crucial property for achieving secure, trustworthy and interpretable deep learning systems is their robustness: small changes to a system's inputs should not result in large changes to its outputs. Mathematically, this means one strives…

机器学习 · 计算机科学 2024-06-04 Bernd Prach , Christoph H. Lampert

Due to their susceptibility to adversarial perturbations, neural networks (NNs) are hardly used in safety-critical applications. One measure of robustness to such perturbations in the input is the Lipschitz constant of the input-output map…

机器学习 · 计算机科学 2021-04-30 Patricia Pauli , Anne Koch , Julian Berberich , Paul Kohler , Frank Allgöwer

Ensuring neural network robustness is essential for the safe and reliable operation of robotic learning systems, especially in perception and decision-making tasks within real-world environments. This paper investigates the robustness of…

机器学习 · 计算机科学 2024-11-01 Abulikemu Abuduweili , Changliu Liu

We investigate robustness of deep feed-forward neural networks when input data are subject to random uncertainties. More specifically, we consider regularization of the network by its Lipschitz constant and emphasize its role. We highlight…

机器学习 · 计算机科学 2019-04-15 Nicolas Couellan

We investigate the effect of explicitly enforcing the Lipschitz continuity of neural networks with respect to their inputs. To this end, we provide a simple technique for computing an upper bound to the Lipschitz constant---for multiple…

机器学习 · 统计学 2020-08-11 Henry Gouk , Eibe Frank , Bernhard Pfahringer , Michael J. Cree

Certified robustness is a desirable property for deep neural networks in safety-critical applications, and popular training algorithms can certify robustness of a neural network by computing a global bound on its Lipschitz constant.…

机器学习 · 计算机科学 2021-11-03 Yujia Huang , Huan Zhang , Yuanyuan Shi , J Zico Kolter , Anima Anandkumar

The Lipschitz constant of the map between the input and output space represented by a neural network is a natural metric for assessing the robustness of the model. We present a new method to constrain the Lipschitz constant of dense deep…

机器学习 · 计算机科学 2023-08-22 Ouail Kitouni , Niklas Nolte , Mike Williams

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…

机器学习 · 计算机科学 2023-01-18 Mahyar Fazlyab , Alexander Robey , Hamed Hassani , Manfred Morari , George J. Pappas

We consider deep neural networks with a Lipschitz continuous activation function and with weight matrices of variable widths. We establish a uniform convergence analysis framework in which sufficient conditions on weight matrices and bias…

机器学习 · 计算机科学 2023-06-05 Yuesheng Xu , Haizhang Zhang

Existing bounds on the generalization error of deep networks assume some form of smooth or bounded dependence on the input variable, falling short of investigating the mechanisms controlling such factors in practice. In this work, we…

机器学习 · 计算机科学 2025-07-24 Matteo Gamba , Hossein Azizpour , Mårten Björkman

Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz constant of a feed-forward neural network, which we refer to as…

机器学习 · 统计学 2018-07-03 Henry Gouk , Bernhard Pfahringer , Eibe Frank , Michael Cree

Deriving sharp and computable upper bounds of the Lipschitz constant of deep neural networks is crucial to formally guarantee the robustness of neural-network based models. We analyse three existing upper bounds written for the $l^2$ norm.…

机器学习 · 计算机科学 2024-10-29 Moreno Pintore , Bruno Després

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…

机器学习 · 统计学 2019-10-28 Kevin Scaman , Aladin Virmaux

This paper tackles the problem of Lipschitz regularization of Convolutional Neural Networks. Lipschitz regularity is now established as a key property of modern deep learning with implications in training stability, generalization,…

机器学习 · 计算机科学 2020-11-10 Alexandre Araujo , Benjamin Negrevergne , Yann Chevaleyre , Jamal Atif

The Lipschitz constant is an important quantity that arises in analysing the convergence of gradient-based optimization methods. It is generally unclear how to estimate the Lipschitz constant of a complex model. Thus, this paper studies an…

机器学习 · 统计学 2023-02-10 Calypso Herrera , Florian Krach , Josef Teichmann

Robust risk minimisation has several advantages: it has been studied with regards to improving the generalisation properties of models and robustness to adversarial perturbation. We bound the distributionally robust risk for a model class…

机器学习 · 统计学 2018-09-06 Zac Cranko , Simon Kornblith , Zhan Shi , Richard Nock

In this paper, we study the problem of optimizing a two-layer artificial neural network that best fits a training dataset. We look at this problem in the setting where the number of parameters is greater than the number of sampled points.…

机器学习 · 计算机科学 2017-11-01 Digvijay Boob , Guanghui Lan

Existing Rademacher complexity bounds for neural networks rely only on norm control of the weight matrices and depend exponentially on depth via a product of the matrix norms. Lower bounds show that this exponential dependence on depth is…

机器学习 · 计算机科学 2020-04-13 Colin Wei , Tengyu Ma
‹ 上一页 1 2 3 10 下一页 ›