English
Related papers

Related papers: Spectrally-normalized margin bounds for neural net…

200 papers

We investigate approaches to regularisation during fine-tuning of deep neural networks. First we provide a neural network generalisation bound based on Rademacher complexity that uses the distance the weights have moved from their initial…

Machine Learning · Statistics 2021-01-18 Henry Gouk , Timothy M. Hospedales , Massimiliano Pontil

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is…

Machine Learning · Computer Science 2022-06-09 Ziquan Liu , Yufei Cui , Antoni B. Chan

A crucial problem in neural networks is to select the most appropriate number of hidden neurons and obtain tight statistical risk bounds. In this work, we present a new perspective towards the bias-variance tradeoff in neural networks. As…

Machine Learning · Computer Science 2020-10-05 Gen Li , Yuantao Gu , Jie Ding

In deep neural networks, the spectral norm of the Jacobian of a layer bounds the factor by which the norm of a signal changes during forward/backward propagation. Spectral norm regularizations have been shown to improve generalization,…

Machine Learning · Computer Science 2021-06-15 Sahil Singla , Soheil Feizi

Several recent papers have discussed utilizing Lipschitz constants to limit the susceptibility of neural networks to adversarial examples. We analyze recently proposed methods for computing the Lipschitz constant. We show that the Lipschitz…

Machine Learning · Computer Science 2018-07-26 Todd Huster , Cho-Yu Jason Chiang , Ritu Chadha

Neural oscillators that originate from second-order ordinary differential equations (ODEs) have shown competitive performance in learning mappings between dynamic loads and responses of complex nonlinear structural systems. Despite this…

Machine Learning · Computer Science 2026-05-11 Zifeng Huang , Konstantin M. Zuev , Yong Xia , Michael Beer

In this paper, we correct an upper bound, presented in~\cite{hs-11}, on the generalisation error of classifiers learned through multiple kernel learning. The bound in~\cite{hs-11} uses Rademacher complexity and has an\emph{additive}…

Machine Learning · Computer Science 2014-05-13 Zakria Hussain , John Shawe-Taylor , Mario Marchand

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

Important research efforts have focused on the design and training of neural networks with a controlled Lipschitz constant. The goal is to increase and sometimes guarantee the robustness against adversarial attacks. Recent promising…

Machine Learning · Computer Science 2023-10-30 Alexandre Araujo , Aaron Havens , Blaise Delattre , Alexandre Allauzen , Bin Hu

As shown in recent research, deep neural networks can perfectly fit randomly labeled data, but with very poor accuracy on held out data. This phenomenon indicates that loss functions such as cross-entropy are not a reliable indicator of…

Machine Learning · Statistics 2019-06-13 Yiding Jiang , Dilip Krishnan , Hossein Mobahi , Samy Bengio

In this paper, we show that although the minimizers of cross-entropy and related classification losses are off at infinity, network weights learned by gradient flow converge in direction, with an immediate corollary that network…

Machine Learning · Computer Science 2020-10-27 Ziwei Ji , Matus Telgarsky

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 derive a new Rademacher complexity bound for deep neural networks using Koopman operators, group representations, and reproducing kernel Hilbert spaces (RKHSs). The proposed bound describes why the models with high-rank weight matrices…

Machine Learning · Computer Science 2026-02-25 Yuka Hashimoto , Sho Sonoda , Isao Ishikawa , Masahiro Ikeda

We prove global Lipschitz regularity for a wide class of convex variational integrals among all functions in $W^{1,1}$ with prescribed (sufficiently regular) boundary values, which are not assumed to satisfy any geometrical constraint (as…

Analysis of PDEs · Mathematics 2018-02-28 Miroslav Bulíček , Erika Maringová , Bianca Stroffolini , Anna Verde

Analysing statistical properties of neural networks is a central topic in statistics and machine learning. However, most results in the literature focus on the properties of the neural network minimizing the training error. The goal of this…

Statistics Theory · Mathematics 2022-02-04 Laura Tinsi , Arnak S. Dalalyan

Oversmoothing has been claimed as a primary bottleneck for multi-layered graph neural networks (GNNs). Multiple analyses have examined how and why oversmoothing occurs. However, none of the prior work addressed how optimization is performed…

Machine Learning · Computer Science 2024-10-08 MoonJeong Park , Dongwoo Kim

This paper is concerned with boundary regularity estimates in the homogenization of elliptic equations with rapidly oscillating and high-contrast coefficients. We establish uniform nontangential-maximal-function estimates for the Dirichlet,…

Analysis of PDEs · Mathematics 2021-05-28 Zhongwei Shen

We consider learning two layer neural networks using stochastic gradient descent. The mean-field description of this learning dynamics approximates the evolution of the network weights by an evolution in the space of probability…

Machine Learning · Statistics 2019-02-19 Song Mei , Theodor Misiakiewicz , Andrea Montanari

Prior work (Klochkov $\&$ Zhivotovskiy, 2021) establishes at most $O\left(\log (n)/n\right)$ excess risk bounds via algorithmic stability for strongly-convex learners with high probability. We show that under the similar common assumptions…

Machine Learning · Computer Science 2025-10-31 Bowei Zhu , Shaojie Li , Mingyang Yi , Yong Liu

Weight sharing, equivariance, and local filters, as in convolutional neural networks, are believed to contribute to the sample efficiency of neural networks. However, it is not clear how each one of these design choices contributes to the…

Machine Learning · Computer Science 2025-01-27 Arash Behboodi , Gabriele Cesa
‹ Prev 1 8 9 10 Next ›