English
Related papers

Related papers: Exploring the Gap between Tolerant and Non-toleran…

200 papers

Learning from a limited number of samples is challenging since the learned model can easily become overfitted based on the biased distribution formed by only a few training examples. In this paper, we calibrate the distribution of these…

Machine Learning · Computer Science 2021-08-17 Shuo Yang , Lu Liu , Min Xu

Many machine learning models appear to deploy effortlessly under distribution shift, and perform well on a target distribution that is considerably different from the training distribution. Yet, learning theory of distribution shift bounds…

Machine Learning · Computer Science 2024-05-30 Robi Bhattacharjee , Nick Rittler , Kamalika Chaudhuri

Expectations of multivariate functions with missing labels occur in various fields such as transfer learning and average treatment effects. Although non-parametric estimators based on nearest-neighbour matching are frequently used in this…

Statistics Theory · Mathematics 2026-05-18 Simon Viel

We study the problem of efficiently detecting Out-of-Distribution (OOD) samples at test time in supervised and unsupervised learning contexts. While ML models are typically trained under the assumption that training and test data stem from…

Machine Learning · Computer Science 2024-05-13 Alberto Caron , Chris Hicks , Vasilios Mavroudis

Given samples from an unknown distribution $p$ and a description of a distribution $q$, are $p$ and $q$ close or far? This question of "identity testing" has received significant attention in the case of testing whether $p$ and $q$ are…

Data Structures and Algorithms · Computer Science 2017-11-01 Constantinos Daskalakis , Gautam Kamath , John Wright

In this paper, we consider the problem of testing properties of joint distributions under the Conditional Sampling framework. In the standard sampling model, the sample complexity of testing properties of joint distributions is exponential…

Computational Complexity · Computer Science 2022-08-03 Rishiraj Bhattacharyya , Sourav Chakraborty

We study the question of identity testing for structured distributions. More precisely, given samples from a {\em structured} distribution $q$ over $[n]$ and an explicit distribution $p$ over $[n]$, we wish to distinguish whether $q=p$…

Data Structures and Algorithms · Computer Science 2014-10-10 Ilias Diakonikolas , Daniel M. Kane , Vladimir Nikishkin

We study the problem of Out-of-Distribution (OOD) detection, that is, detecting whether a learning algorithm's output can be trusted at inference time. While a number of tests for OOD detection have been proposed in prior work, a formal…

Machine Learning · Statistics 2023-09-19 Akshayaa Magesh , Venugopal V. Veeravalli , Anirban Roy , Susmit Jha

We study the basic statistical problem of testing whether normally distributed $n$-dimensional data has been truncated, i.e. altered by only retaining points that lie in some unknown truncation set $S \subseteq \mathbb{R}^n$. As our main…

Data Structures and Algorithms · Computer Science 2024-11-25 Anindya De , Shivam Nadimpalli , Rocco A. Servedio

We initiate a systematic investigation of distribution testing in the framework of algorithmic replicability. Specifically, given independent samples from a collection of probability distributions, the goal is to characterize the sample…

Machine Learning · Computer Science 2025-07-04 Ilias Diakonikolas , Jingyi Gao , Daniel Kane , Sihan Liu , Christopher Ye

The primary problem in property testing is to decide whether a given function satisfies a certain property, or is far from any function satisfying it. This crucially requires a notion of distance between functions. The most prevalent notion…

Discrete Mathematics · Computer Science 2014-04-04 Deeparnab Chakrabarty , Kashyap Dixit , Madhav Jha , C. Seshadhri

There is a well-known problem in Null Hypothesis Significance Testing: many statistically significant results fail to replicate in subsequent experiments. We show that this problem arises because standard `point-form null' significance…

Methodology · Statistics 2025-02-06 Fintan Costello , Paul Watts

We study hypothesis testing (aka state certification) in the non-identically distributed setting. A recent work (Garg et al. 2023) considered the classical case, in which one is given (independent) samples from $T$ unknown probability…

Quantum Physics · Physics 2025-10-08 Giacomo De Palma , Marco Fanizza , Connor Mowry , Ryan O'Donnell

We study the equivalence testing problem where the goal is to determine if the given two unknown distributions on $[n]$ are equal or $\epsilon$-far in the total variation distance in the conditional sampling model (CFGM, SICOMP16; CRS,…

Data Structures and Algorithms · Computer Science 2023-08-23 Diptarka Chakraborty , Sourav Chakraborty , Gunjan Kumar

Rapid progress in representation learning has led to a proliferation of embedding models, and to associated challenges of model selection and practical application. It is non-trivial to assess a model's generalizability to new, candidate…

Machine Learning · Computer Science 2022-02-18 Leo Betthauser , Urszula Chajewska , Maurice Diesendruck , Rohith Pesala

A nonparametric anomalous hypothesis testing problem is investigated, in which there are totally n sequences with s anomalous sequences to be detected. Each typical sequence contains m independent and identically distributed (i.i.d.)…

Machine Learning · Computer Science 2016-12-15 Shaofeng Zou , Yingbin Liang , H. Vincent Poor , Xinghua Shi

In the real world, a learning system could receive an input that is unlike anything it has seen during training. Unfortunately, out-of-distribution samples can lead to unpredictable behaviour. We need to know whether any given input belongs…

Machine Learning · Computer Science 2019-08-21 Alireza Shafaei , Mark Schmidt , James J. Little

We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample domains, but where we have many samples in each domain. Our…

Machine Learning · Computer Science 2011-05-05 Dean Foster , Sham Kakade , Ruslan Salakhutdinov

Uniformity testing is arguably one of the most fundamental distribution testing problems. Given sample access to an unknown distribution $\mathbf{p}$ on $[n]$, one must decide if $\mathbf{p}$ is uniform or $\varepsilon$-far from uniform (in…

Machine Learning · Statistics 2024-10-16 Sihan Liu , Christopher Ye

We study the following distribution clustering problem: Given a hidden partition of $k$ distributions into two groups, such that the distributions within each group are the same, and the two distributions associated with the two clusters…

Data Structures and Algorithms · Computer Science 2025-12-10 Gunjan Kumar , Yash Pote , Jonathan Scarlett