English
Related papers

Related papers: Distribution-Dependent Sample Complexity of Large …

200 papers

Understanding the generalization of deep neural networks is one of the most important tasks in deep learning. Although much progress has been made, theoretical error bounds still often behave disparately from empirical observations. In this…

Machine Learning · Computer Science 2021-11-09 Ching-Yao Chuang , Youssef Mroueh , Kristjan Greenewald , Antonio Torralba , Stefanie Jegelka

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…

Machine Learning · Computer Science 2020-04-13 Colin Wei , Tengyu Ma

We study the problem of learning nonparametric distributions in a finite mixture, and establish tight bounds on the sample complexity for learning the component distributions in such models. Namely, we are given i.i.d. samples from a pdf…

Machine Learning · Computer Science 2023-07-06 Bryon Aragam , Wai Ming Tai

We deal with the problem of the adaptive estimation of the $\mathbb{L}_2$-norm of a probability density on $\mathbb{R}^d$, $d\geq 1$, from independent observations. The unknown density is assumed to be uniformly bounded and to belong to the…

Statistics Theory · Mathematics 2024-05-28 Galatia Cleanthous , Athanasios G. Georgiadis , Oleg V. Lepski

We present a new adaptive algorithm for learning discrete distributions under distribution drift. In this setting, we observe a sequence of independent samples from a discrete distribution that is changing over time, and the goal is to…

Machine Learning · Computer Science 2024-03-11 Alessio Mazzetto

A classical condition for fast learning rates is the margin condition, first introduced by Mammen and Tsybakov. We tackle in this paper the problem of adaptivity to this condition in the context of model selection, in a general learning…

Statistics Theory · Mathematics 2011-05-02 Sylvain Arlot , Peter L. Bartlett

This paper expands the analysis of randomized low-rank approximation beyond the Gaussian distribution to four classes of random matrices: (1) independent sub-Gaussian entries, (2) independent sub-Gaussian columns, (3) independent bounded…

Numerical Analysis · Mathematics 2023-08-14 Arvind K. Saibaba , Agnieszka Międlar

We study how well generative adversarial networks (GAN) learn probability distributions from finite samples by analyzing the convergence rates of these models. Our analysis is based on a new oracle inequality that decomposes the estimation…

Machine Learning · Computer Science 2022-05-26 Yunfei Yang

Gaussian distributions are widely used in Bayesian variational inference to approximate intractable posterior densities, but the ability to accommodate skewness can improve approximation accuracy significantly, when data or prior…

Methodology · Statistics 2025-02-05 Linda S. L. Tan , Aoxiang Chen

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 work, we give efficient algorithms for privately estimating a Gaussian distribution in both pure and approximate differential privacy (DP) models with optimal dependence on the dimension in the sample complexity. In the pure DP…

Data Structures and Algorithms · Computer Science 2023-06-02 Daniel Alabi , Pravesh K. Kothari , Pranay Tankala , Prayaag Venkat , Fred Zhang

This paper establishes sharp dimension-free concentration and expectation bounds for the deviation of a sample cross-covariance matrix from its mean. For sub-Gaussian random vectors, we prove a high-probability operator-norm bound governed…

Probability · Mathematics 2026-05-19 Jiaheng Chen , Daniel Sanz-Alonso

The problem of learning single index and multi index models has gained significant interest as a fundamental task in high-dimensional statistics. Many recent works have analysed gradient-based methods, particularly in the setting of…

Machine Learning · Computer Science 2025-07-22 Elisabetta Cornacchia , Dan Mikulincer , Elchanan Mossel

In this work, we give a novel general approach for distribution testing. We describe two techniques: our first technique gives sample-optimal testers, while our second technique gives matching sample lower bounds. As a consequence, we…

Data Structures and Algorithms · Computer Science 2016-05-10 Ilias Diakonikolas , Daniel M. Kane

We study the tradeoff between sample complexity and round complexity in on-demand sampling, where the learning algorithm adaptively samples from $k$ distributions over a limited number of rounds. In the realizable setting of…

Machine Learning · Computer Science 2025-11-20 Nika Haghtalab , Omar Montasser , Mingda Qiao

We consider the optimization problem of minimizing the logistic loss with gradient descent to train a linear model for binary classification with separable data. With a budget of $T$ iterations, it was recently shown that an accelerated…

Machine Learning · Computer Science 2026-02-16 Michael Crawshaw , Mingrui Liu

Classification margins are commonly used to estimate the generalization ability of machine learning models. We present an empirical study of these margins in artificial neural networks. A global estimate of margin size is usually used in…

Machine Learning · Computer Science 2023-02-15 Marthinus W. Theunissen , Coenraad Mouton , Marelie H. Davel

We prove that a classifier with a Barron-regular decision boundary can be approximated with a rate of high polynomial degree by ReLU neural networks with three hidden layers when a margin condition is assumed. In particular, for strong…

Machine Learning · Computer Science 2025-01-13 Jonathan García , Philipp Petersen

Binary classification is a common statistical learning problem in which a model is estimated on a set of covariates for some outcome indicating the membership of one of two classes. In the literature, there exists a distinction between hard…

Machine Learning · Statistics 2014-11-20 Patrick K. Kimes , D. Neil Hayes , J. S. Marron , Yufeng Liu

The generalization mystery of overparametrized deep nets has motivated efforts to understand how gradient descent (GD) converges to low-loss solutions that generalize well. Real-life neural networks are initialized from small random values…

Machine Learning · Computer Science 2021-11-10 Kaifeng Lyu , Zhiyuan Li , Runzhe Wang , Sanjeev Arora