English
Related papers

Related papers: Depth Separation in Norm-Bounded Infinite-Width Ne…

200 papers

We present polynomial time and sample efficient algorithms for learning an unknown depth-2 feedforward neural network with general ReLU activations, under mild non-degeneracy assumptions. In particular, we consider learning an unknown…

Machine Learning · Computer Science 2021-08-03 Pranjal Awasthi , Alex Tang , Aravindan Vijayaraghavan

It has been experimentally observed in recent years that multi-layer artificial neural networks have a surprising ability to generalize, even when trained with far more parameters than observations. Is there a theoretical basis for this?…

Machine Learning · Statistics 2018-09-19 Andrew R. Barron , Jason M. Klusowski

By classifying infinite-width neural networks and identifying the *optimal* limit, Tensor Programs IV and V demonstrated a universal way, called $\mu$P, for *widthwise hyperparameter transfer*, i.e., predicting optimal hyperparameters of…

Neural and Evolutionary Computing · Computer Science 2023-10-13 Greg Yang , Dingli Yu , Chen Zhu , Soufiane Hayou

Over-parameterized neural networks generalize well in practice without any explicit regularization. Although it has not been proven yet, empirical evidence suggests that implicit regularization plays a crucial role in deep learning and…

Machine Learning · Computer Science 2019-03-07 Masayoshi Kubo , Ryotaro Banno , Hidetaka Manabe , Masataka Minoji

Statistical learning theory provides bounds on the necessary number of training samples needed to reach a prescribed accuracy in a learning problem formulated over a given target class. This accuracy is typically measured in terms of a…

Machine Learning · Computer Science 2023-03-01 Julius Berner , Philipp Grohs , Felix Voigtlaender

Driven by privacy protection laws and regulations, unlearning in Large Language Models (LLMs) is gaining increasing attention. However, current research often neglects the interpretability of the unlearning process, particularly concerning…

Machine Learning · Computer Science 2025-04-10 Xiaohua Feng , Yuyuan Li , Chengye Wang , Junlin Liu , Li Zhang , Chaochao Chen

A key challenge facing deep learning is that neural networks are often not robust to shifts in the underlying data distribution. We study this problem from the perspective of the statistical concept of parameter identification.…

Machine Learning · Computer Science 2022-02-18 Kan Xu , Hamsa Bastani , Osbert Bastani

As the success of deep learning reaches more grounds, one would like to also envision the potential limits of deep learning. This paper gives a first set of results proving that certain deep learning algorithms fail at learning certain…

Machine Learning · Computer Science 2019-04-30 Emmanuel Abbe , Colin Sandon

Covering numbers of (deep) ReLU networks have been used to characterize approximation-theoretic performance, to upper-bound prediction error in nonparametric regression, and to quantify classification capacity. These results rely on…

Machine Learning · Statistics 2026-03-04 Weigutian Ou , Helmut Bölcskei

One of the arguments to explain the success of deep learning is the powerful approximation capacity of deep neural networks. Such capacity is generally accompanied by the explosive growth of the number of parameters, which, in turn, leads…

Machine Learning · Computer Science 2022-09-15 Zuowei Shen , Haizhao Yang , Shijun Zhang

This article is concerned with the approximation and expressive powers of deep neural networks. This is an active research area currently producing many interesting papers. The results most commonly found in the literature prove that neural…

Machine Learning · Computer Science 2019-05-08 I. Daubechies , R. DeVore , S. Foucart , B. Hanin , G. Petrova

We consider infinitely dimensional classes of functions and instead of the relative error setting, which was used in previous papers on the integral norm discretization, we consider the absolute error setting. We demonstrate how known…

Numerical Analysis · Mathematics 2022-03-15 V. N. Temlyakov

Learning with neural networks relies on the complexity of the representable functions, but more importantly, the particular assignment of typical parameters to functions of different complexity. Taking the number of activation regions as a…

Machine Learning · Statistics 2021-12-17 Hanna Tseran , Guido Montúfar

We study the diversity of the features learned by a two-layer neural network trained with the least squares loss. We measure the diversity by the average $L_2$-distance between the hidden-layer features and theoretically investigate how…

Machine Learning · Computer Science 2023-06-14 Firas Laakom , Jenni Raitoharju , Alexandros Iosifidis , Moncef Gabbouj

While neural networks are used for classification tasks across domains, a long-standing open problem in machine learning is determining whether neural networks trained using standard procedures are optimal for classification, i.e., whether…

Machine Learning · Computer Science 2023-05-03 Adityanarayanan Radhakrishnan , Mikhail Belkin , Caroline Uhler

Estimating the relative importance of each sample in a training set has important practical and theoretical value, such as in importance sampling or curriculum learning. This kind of focus on individual samples invokes the concept of…

Machine Learning · Computer Science 2019-01-09 Seung-Geon Lee , Jaedeok Kim , Hyun-Joo Jung , Yoonsuck Choe

Sample weighting is widely used in deep learning. A large number of weighting methods essentially utilize the learning difficulty of training samples to calculate their weights. In this study, this scheme is called difficulty-based…

Machine Learning · Computer Science 2023-01-13 Xiaoling Zhou , Ou Wu , Weiyao Zhu , Ziyang Liang

Recurrent Neural Networks (RNNs) are very successful at solving challenging problems with sequential data. However, this observed efficiency is not yet entirely explained by theory. It is known that a certain class of multiplicative RNNs…

Machine Learning · Computer Science 2019-01-31 Valentin Khrulkov , Oleksii Hrinchuk , Ivan Oseledets

In this article we study high-dimensional approximation capacities of shallow and deep artificial neural networks (ANNs) with the rectified linear unit (ReLU) activation. In particular, it is a key contribution of this work to reveal that…

Numerical Analysis · Mathematics 2023-01-23 Lukas Gonon , Robin Graeber , Arnulf Jentzen

Overparameterized fully-connected neural networks have been shown to behave like kernel models when trained with gradient descent, under mild conditions on the width, the learning rate, and the parameter initialization. In the limit of…

Machine Learning · Computer Science 2025-11-11 William St-Arnaud , Margarida Carvalho , Golnoosh Farnadi