English
Related papers

Related papers: On the Sample Complexity of Two-Layer Networks: Li…

200 papers

Research in computational deep learning has directed considerable efforts towards hardware-oriented optimisations for deep neural networks, via the simplification of the activation functions, or the quantization of both activations and…

Machine Learning · Computer Science 2020-11-04 Gian Paolo Leonardi , Matteo Spallanzani

We study non-convex empirical risk minimization for learning halfspaces and neural networks. For loss functions that are $L$-Lipschitz continuous, we present algorithms to learn halfspaces and multi-layer neural networks that achieve…

Machine Learning · Computer Science 2015-11-26 Yuchen Zhang , Jason D. Lee , Martin J. Wainwright , Michael I. Jordan

We consider the problem of active learning for single neuron models, also sometimes called ``ridge functions'', in the agnostic setting (under adversarial label noise). Such models have been shown to be broadly effective in modeling…

Machine Learning · Computer Science 2023-07-20 Aarshvi Gajjar , Chinmay Hegde , Christopher Musco

We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the margin-adapted dimension, which is a simple function of the second order statistics of…

Machine Learning · Statistics 2013-09-19 Sivan Sabato , Nathan Srebro , Naftali Tishby

This paper studies the generalization properties of a recently proposed kernel method, the Random Feature models with Learnable Activation Functions (RFLAF). By applying a data-dependent sampling scheme for generating features, we provide…

Machine Learning · Computer Science 2025-10-20 Zailin Ma , Jiansheng Yang , Yaodong Yang

A new non-linear variant of a quantitative extension of the uniform boundedness principle is used to show sharpness of error bounds for univariate approximation by sums of sigmoid and ReLU functions. Single hidden layer feedforward neural…

Functional Analysis · Mathematics 2020-06-18 Steffen Goebbels

We provide several new results on the sample complexity of vector-valued linear predictors (parameterized by a matrix), and more generally neural networks. Focusing on size-independent bounds, where only the Frobenius norm distance of the…

Machine Learning · Computer Science 2023-10-26 Roey Magen , Ohad Shamir

We develop a minimax theory for operator learning, where the goal is to estimate an unknown operator between separable Hilbert spaces from finitely many noisy input-output samples. For uniformly bounded Lipschitz operators, we prove…

Statistics Theory · Mathematics 2026-03-06 Ben Adcock , Gregor Maier , Rahul Parhi

This paper considers the following question: how well can depth-two ReLU networks with randomly initialized bottom-level weights represent smooth functions? We give near-matching upper- and lower-bounds for $L_2$-approximation in terms of…

Machine Learning · Computer Science 2021-09-09 Daniel Hsu , Clayton Sanford , Rocco A. Servedio , Emmanouil-Vasileios Vlatakis-Gkaragkounis

We study the sample complexity of learning ReLU neural networks from the point of view of generalization. Given norm constraints on the weight matrices, a common approach is to estimate the Rademacher complexity of the associated function…

Machine Learning · Computer Science 2024-02-06 Mark Sellke

We study the excess capacity of deep networks in the context of supervised classification. That is, given a capacity measure of the underlying hypothesis class - in our case, empirical Rademacher complexity - to what extent can we (a…

Machine Learning · Computer Science 2023-01-20 Florian Graf , Sebastian Zeng , Bastian Rieck , Marc Niethammer , Roland Kwitt

We study depth separation in infinite-width neural networks, where complexity is controlled by the overall squared $\ell_2$-norm of the weights (sum of squares of all weights in the network). Whereas previous depth separation results…

Machine Learning · Computer Science 2024-02-15 Suzanna Parkinson , Greg Ongie , Rebecca Willett , Ohad Shamir , Nathan Srebro

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…

Machine Learning · Computer Science 2023-01-18 Mahyar Fazlyab , Alexander Robey , Hamed Hassani , Manfred Morari , George J. Pappas

Lipschitz continuity is a crucial functional property of any predictive model, that naturally governs its robustness, generalisation, as well as adversarial vulnerability. Contrary to other works that focus on obtaining tighter bounds and…

Machine Learning · Computer Science 2024-05-16 Grigory Khromov , Sidak Pal Singh

We prove some new results concerning the approximation rate of neural networks with general activation functions. Our first result concerns the rate of approximation of a two layer neural network with a polynomially-decaying non-sigmoidal…

Classical Analysis and ODEs · Mathematics 2021-01-05 Jonathan W. Siegel , Jinchao Xu

We establish improved sample-complexity bounds for sample-based Lindbladian simulation based on the Wave Matrix Lindbladization (WML) algorithm. For a jump operator $L$ with dimension $d$, we derive an explicit non-asymptotic sample…

Quantum Physics · Physics 2026-05-29 Siheon Park , Youngjin Seo , Byeongseon Go , Dhrumil Patel , Mark M. Wilde , Hyukjoon Kwon

We study how the optimization landscape of a neural network deforms as a non-linear activation is introduced through a smooth homotopy. Working first in an abstract local setting - a smooth one-parameter family of objective functions…

Optimization and Control · Mathematics 2026-04-03 Michael Alexander

Smooth activation functions are ubiquitous in modern deep learning, yet their theoretical advantages over non-smooth counterparts remain poorly understood. In this work, we study both approximation and statistical properties of neural…

Machine Learning · Statistics 2026-03-03 Yuhao Liu , Zilin Wang , Lei Wu , Shaobo Zhang

This paper investigates the approximation properties of deep neural networks with piecewise-polynomial activation functions. We derive the required depth, width, and sparsity of a deep neural network to approximate any H\"{o}lder smooth…

Numerical Analysis · Mathematics 2022-12-06 Denis Belomestny , Alexey Naumov , Nikita Puchkin , Sergey Samsonov

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…

Machine Learning · Statistics 2020-08-11 Henry Gouk , Eibe Frank , Bernhard Pfahringer , Michael J. Cree