English
Related papers

Related papers: Testing Convex Truncation

200 papers

The generalization error of a learning algorithm refers to the discrepancy between the loss of a learning algorithm on training data and that on unseen testing data. Various information-theoretic bounds on the generalization error have been…

Information Theory · Computer Science 2025-06-24 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

A result of Spencer states that every collection of $n$ sets over a universe of size $n$ has a coloring of the ground set with $\{-1,+1\}$ of discrepancy $O(\sqrt{n})$. A geometric generalization of this result was given by Gluskin (see…

Data Structures and Algorithms · Computer Science 2014-09-11 Ronen Eldan , Mohit Singh

We consider the problem of distinguishing between two arbitrary black-box distributions defined over the domain [n], given access to $s$ samples from both. It is known that in the worst case O(n^{2/3}) samples is both necessary and…

Data Structures and Algorithms · Computer Science 2011-10-17 Eyal Even Dar , Mark Sandler

In truncated linear regression, samples $(x,y)$ are shown only when the outcome $y$ falls inside a certain survival set $S^\star$ and the goal is to estimate the unknown $d$-dimensional regressor $w^\star$. This problem has a long history…

Machine Learning · Statistics 2026-05-25 Alexandros Kouridakis , Anay Mehrotra , Alkis Kalavasis , Constantine Caramanis

We consider the least-squares regression problem and provide a detailed asymptotic analysis of the performance of averaged constant-step-size stochastic gradient descent (a.k.a. least-mean-squares). In the strongly-convex case, we provide…

Machine Learning · Computer Science 2014-12-02 Alexandre Défossez , Francis Bach

We study stochastic graph optimization problems in a novel distributed setting. As in the standard centralized setting, a random subgraph $G^*$ of a known base graph $G$ is realized by including each edge $e$ independently with a known…

Data Structures and Algorithms · Computer Science 2026-05-21 Keren Censor-Hillel , Aditi Dudeja , George Giakkoupis

In this article we recover the distribution function (and possible density) of an arbitrary random variable that is subject to an additive measurement error. This problem is also known as deconvolution and has a long tradition in…

Statistics Theory · Mathematics 2025-10-07 Henrik Kaiser

The two-sample problem, which consists in testing whether independent samples on $\mathbb{R}^d$ are drawn from the same (unknown) distribution, finds applications in many areas. Its study in high-dimension is the subject of much attention,…

Statistics Theory · Mathematics 2023-02-09 Stephan Clémençon , Myrto Limnios , Nicolas Vayatis

In this paper, we have established a new framework of truncated inverse sampling for estimating mean values of non-negative random variables such as binomial, Poisson, hyper-geometrical, and bounded variables. We have derived explicit…

Statistics Theory · Mathematics 2013-11-05 Xinjia Chen

This paper develops an analytical method of truncating inequality constrained Gaussian distributed variables where the constraints are themselves described by Gaussian distributions. Existing truncation methods either assume hard…

Systems and Control · Computer Science 2016-06-08 Andrew W. Palmer , Andrew J. Hill , Steven J. Scheding

We show that, under a standard hardness assumption, there is no computationally efficient algorithm that given $n$ samples from an unknown distribution can give valid answers to $n^{3+o(1)}$ adaptively chosen statistical queries. A…

Machine Learning · Computer Science 2014-08-08 Moritz Hardt , Jonathan Ullman

We study a new framework for property testing of probability distributions, by considering distribution testing algorithms that have access to a conditional sampling oracle.* This is an oracle that takes as input a subset $S \subseteq [N]$…

Data Structures and Algorithms · Computer Science 2015-01-19 Clement Canonne , Dana Ron , Rocco A. Servedio

We consider a variant of online convex optimization in which both the instances (input vectors) and the comparator (weight vector) are unconstrained. We exploit a natural scale invariance symmetry in our unconstrained setting: the…

Machine Learning · Computer Science 2017-08-24 Wojciech Kotłowski

The distribution of the sum of independent identically distributed uniform random variables is well-known. However, it is sometimes necessary to analyze data which have been drawn from different uniform distributions. By inverting the…

Statistics Theory · Mathematics 2010-05-25 David M. Bradley , Ramesh C. Gupta

In this paper, we test whether two datasets share a common clustering structure. As a leading example, we focus on comparing clustering structures in two independent random samples from two mixtures of multivariate normal distributions.…

Statistics Theory · Mathematics 2022-11-21 Chao Gao , Zongming Ma

Two-sample hypothesis testing-determining whether two sets of data are drawn from the same distribution-is a fundamental problem in statistics and machine learning with broad scientific applications. In the context of nonparametric testing,…

Machine Learning · Statistics 2026-04-21 Antoine Chatalic , Marco Letizia , Nicolas Schreuder , Lorenzo Rosasco

Our goal is to develop a general strategy to decompose a random variable $X$ into multiple independent random variables, without sacrificing any information about unknown parameters. A recent paper showed that for some well-known natural…

Methodology · Statistics 2025-12-23 Ameer Dharamshi , Anna Neufeld , Keshav Motwani , Lucy L. Gao , Daniela Witten , Jacob Bien

This article provides a thorough meta-analysis of the anomaly detection problem. To accomplish this we first identify approaches to benchmarking anomaly detection algorithms across the literature and produce a large corpus of anomaly…

Artificial Intelligence · Computer Science 2016-08-29 Andrew Emmott , Shubhomoy Das , Thomas Dietterich , Alan Fern , Weng-Keen Wong

Randomized algorithms depend on accurate sampling from probability distributions, as their correctness and performance hinge on the quality of the generated samples. However, even for common distributions like Binomial, exact sampling is…

Computation · Statistics 2025-06-17 Uddalok Sarkar , Sourav Chakraborty , Kuldeep S. Meel

We develop a novel unified randomized block-coordinate primal-dual algorithm to solve a class of nonsmooth constrained convex optimization problems, which covers different existing variants and model settings from the literature. We prove…

Optimization and Control · Mathematics 2021-10-29 Quoc Tran-Dinh , Deyi Liu