English
Related papers

Related papers: A Sample Complexity Measure with Applications to L…

200 papers

We derive bounds on the sample complexity of empirical risk minimization (ERM) in the context of minimizing non-convex risks that admit the strict saddle property. Recent progress in non-convex optimization has yielded efficient algorithms…

Machine Learning · Computer Science 2017-06-06 Alon Gonen , Shai Shalev-Shwartz

Uniformity testing is one of the most well-studied problems in property testing, with many known test statistics, including ones based on counting collisions, singletons, and the empirical TV distance. It is known that the optimal sample…

Machine Learning · Statistics 2022-06-23 Shivam Gupta , Eric Price

Binary segmentation is the classic greedy algorithm which recursively splits a sequential data set by optimizing some loss or likelihood function. Binary segmentation is widely used for changepoint detection in data sets measured over space…

Machine Learning · Computer Science 2024-10-14 Toby Dylan Hocking

The theoretical analysis of spectral clustering mainly focuses on consistency, while there is relatively little research on its generalization performance. In this paper, we study the excess risk bounds of the popular spectral clustering…

Machine Learning · Computer Science 2022-07-19 Shaojie Li , Sheng Ouyang , Yong Liu

The Expectation-Maximization (EM) algorithm is a widely used method for maximum likelihood estimation in models with latent variables. For estimating mixtures of Gaussians, its iteration can be viewed as a soft version of the k-means…

Machine Learning · Statistics 2017-06-06 Constantinos Daskalakis , Christos Tzamos , Manolis Zampetakis

This paper considers batch Reinforcement Learning (RL) with general value function approximation. Our study investigates the minimal assumptions to reliably estimate/minimize Bellman error, and characterizes the generalization performance…

Machine Learning · Computer Science 2021-03-26 Yaqi Duan , Chi Jin , Zhiyuan Li

The challenges posed by complex stochastic models used in computational ecology, biology and genetics have stimulated the development of approximate approaches to statistical inference. Here we focus on Synthetic Likelihood (SL), a…

Methodology · Statistics 2017-06-09 Matteo Fasiolo , Simon N. Wood , Florian Hartig , Mark V. Bravington

An algorithm is proposed, analyzed, and tested for solving continuous nonlinear-equality-constrained optimization problems where the objective and constraint functions are defined by expectations or averages over large, finite numbers of…

Optimization and Control · Mathematics 2026-05-14 Frank E. Curtis , Lingjun Guo , Daniel P. Robinson

The Metropolis-Hastings (MH) algorithm is one of the most widely used Markov Chain Monte Carlo schemes for generating samples from Bayesian posterior distributions. The algorithm is asymptotically exact, flexible and easy to implement.…

Methodology · Statistics 2026-03-10 Estevão Prado , Christopher Nemeth , Chris Sherlock

In this paper, we consider the problem of replicable realizable PAC learning. We construct a particularly hard learning problem and show a sample complexity lower bound with a close to $(\log|H|)^{3/2}$ dependence on the size of the…

Machine Learning · Computer Science 2026-02-24 Kasper Green Larsen , Markus Engelund Mathiasen , Chirag Pabbaraju , Clement Svendsen

Subsampling is an effective approach to alleviate the computational burden associated with large-scale datasets. Nevertheless, existing subsampling estimators incur a substantial loss in estimation efficiency compared to estimators based on…

Methodology · Statistics 2025-09-25 Miaomiao Su , Ruoyu Wang

We propose a new estimator for the high-dimensional linear regression model with observation error in the design where the number of coefficients is potentially larger than the sample size. The main novelty of our procedure is that the…

Methodology · Statistics 2019-09-09 Alexandre Belloni , Abhishek Kaul , Mathieu Rosenbaum

Sampling is often a necessary evil to reduce the processing and storage costs of distributed tracing. In this work, we describe a scalable and adaptive sampling approach that can preserve events of interest better than the widely used…

Data Structures and Algorithms · Computer Science 2021-07-19 Otmar Ertl

The goal of importance sampling is to estimate the expected value of a given function with respect to a probability measure $\nu$ using a random sample of size $n$ drawn from a different probability measure $\mu$. If the two measures $\mu$…

Probability · Mathematics 2017-06-22 Sourav Chatterjee , Persi Diaconis

We analyze the sample complexity of learning from multiple experiments where the experimenter has a total budget for obtaining samples. In this problem, the learner should choose a hypothesis that performs well with respect to multiple…

Machine Learning · Computer Science 2019-07-16 Longyun Guo , Jean Honorio , John Morgan

We study the sample complexity of semi-supervised learning (SSL) and introduce new assumptions based on the mismatch between a mixture model learned from unlabeled data and the true mixture model induced by the (unknown) class conditional…

Machine Learning · Computer Science 2018-09-11 Chen Dan , Liu Leqi , Bryon Aragam , Pradeep Ravikumar , Eric P. Xing

This paper addresses the challenging computational problem of estimating intractable expectations over discrete domains. Existing approaches, including Monte Carlo and Russian Roulette estimators, are consistent but often require a large…

Machine Learning · Statistics 2025-12-19 Sophia Seulkee Kang , François-Xavier Briol , Toni Karvonen , Zonghao Chen

The generalization ability of minimizers of the empirical risk in the context of binary classification has been investigated under a wide variety of complexity assumptions for the collection of classifiers over which optimization is…

Statistics Theory · Mathematics 2019-01-21 Clémençon Stephan , Patrice Bertail , Guillaume Papa

A remarkable recent paper by Rubinfeld and Vasilyan (2022) initiated the study of \emph{testable learning}, where the goal is to replace hard-to-verify distributional assumptions (such as Gaussianity) with efficiently testable ones and to…

Machine Learning · Computer Science 2022-11-28 Aravind Gollakota , Adam R. Klivans , Pravesh K. Kothari

The task of the binary classification problem is to determine which of two distributions has generated a length-$n$ test sequence. The two distributions are unknown; two training sequences of length $N$, one from each distribution, are…

Information Theory · Computer Science 2016-04-18 Dayu Huang , Sean Meyn