English
Related papers

Related papers: Telling Two Distributions Apart: a Tight Character…

200 papers

We consider the problem of testing whether an unknown and arbitrary set $S \subseteq \mathbb{R}^n$ (given as a black-box membership oracle) is convex, versus $\varepsilon$-far from every convex set, under the standard Gaussian distribution.…

Computational Complexity · Computer Science 2024-10-24 Xi Chen , Anindya De , Shivam Nadimpalli , Rocco A. Servedio , Erik Waingarten

Independence testing is a fundamental problem in statistical inference: given samples from a joint distribution $p$ over multiple random variables, the goal is to determine whether $p$ is a product distribution or is $\epsilon$-far from all…

Machine Learning · Statistics 2026-03-06 Maryam Aliakbarpour , Alireza Azizi , Ria Stevens

A standard approach in pattern classification is to estimate the distributions of the label classes, and then to apply the Bayes classifier to the estimates of the distributions in order to classify unlabeled examples. As one might expect,…

Machine Learning · Computer Science 2007-05-23 Nick Palmer , Paul W. Goldberg

Although multi-label learning can deal with many problems with label ambiguity, it does not fit some real applications well where the overall distribution of the importance of the labels matters. This paper proposes a novel learning…

Machine Learning · Computer Science 2016-04-06 Xin Geng

We give new characterizations of the sample complexity of answering linear queries (statistical queries) in the local and central models of differential privacy: *In the non-interactive local model, we give the first approximate…

Data Structures and Algorithms · Computer Science 2019-11-20 Alexander Edmonds , Aleksandar Nikolov , Jonathan Ullman

$\renewcommand{\Re}{\mathbb{R}}$Given a set $P$ of $n$ points in $\Re^d$, consider the problem of computing $k$ subsets of $P$ that form clusters that are well-separated from each other, and each of them is large (cardinality wise). We…

Computational Geometry · Computer Science 2021-06-11 Sariel Har-Peled , Joseph Rogge

Statistical samples, in order to be representative, have to be drawn from a population in a random and unbiased way. Nevertheless, it is common practice in the field of model-based diagnosis to make estimations from (biased) best-first…

Artificial Intelligence · Computer Science 2022-08-05 Patrick Rodler , Fatima Elichanova

Low-dimensional embedding, manifold learning, clustering, classification, and anomaly detection are among the most important problems in machine learning. The existing methods usually consider the case when each instance has a fixed,…

Machine Learning · Computer Science 2012-02-20 Barnabas Poczos , Liang Xiong , Jeff Schneider

It is shown that space-time may possess the differentiability properties of manifolds as well as the ultraviolet finiteness properties of lattices. Namely, if a field's amplitudes are given on any sufficiently dense set of discrete points…

General Relativity and Quantum Cosmology · Physics 2016-11-09 Achim Kempf

We make two contributions to the problem of estimating the $L_1$ calibration error of a binary classifier from a finite dataset. First, we provide an upper bound for any classifier where the calibration function has bounded variation.…

NLP practitioners often want to take existing trained models and apply them to data from new domains. While fine-tuning or few-shot learning can be used to adapt a base model, there is no single recipe for making these techniques work;…

Computation and Language · Computer Science 2022-03-16 Xi Ye , Greg Durrett

Suppose one desires to randomly sample a pair of objects such as socks, hoping to get a matching pair. Even in the simplest situation for sampling, which is sampling with replacement, the innocent phrase "the distribution of the color of a…

Probability · Mathematics 2013-06-04 Richard Arratia , Stephen DeSalvo

The most basic assumption used in statistical learning theory is that training data and test data are drawn from the same underlying distribution. Unfortunately, in many applications, the "in-domain" test data is drawn from a distribution…

Machine Learning · Computer Science 2011-09-30 H. Daume , D. Marcu

The partial coloring method is one of the most powerful and widely used method in combinatorial discrepancy problems. However, in many cases it leads to sub-optimal bounds as the partial coloring step must be iterated a logarithmic number…

Data Structures and Algorithms · Computer Science 2017-07-13 Nikhil Bansal , Shashwat Garg

Two old conjectures from problem sections, one of which from SIAM Review, concern the question of finding distributions that maximize P(Sn <= t), where Sn is the sum of i.i.d. random variables X1, ..., Xn on the interval [0,1], satisfying…

Probability · Mathematics 2008-08-13 Ludolf E. Meester

A Poisson Binomial distribution over $n$ variables is the distribution of the sum of $n$ independent Bernoullis. We provide a sample near-optimal algorithm for testing whether a distribution $P$ supported on $\{0,...,n\}$ to which we have…

Data Structures and Algorithms · Computer Science 2014-10-15 Jayadev Acharya , Constantinos Daskalakis

We give highly efficient algorithms, and almost matching lower bounds, for a range of basic statistical problems that involve testing and estimating the L_1 distance between two k-modal distributions $p$ and $q$ over the discrete domain…

Data Structures and Algorithms · Computer Science 2011-12-26 Constantinos Daskalakis , Ilias Diakonikolas , Rocco A. Servedio , Gregory Valiant , Paul Valiant

Two-sample testing, where we aim to determine whether two distributions are equal or not equal based on samples from each one, is challenging if we cannot place assumptions on the properties of the two distributions. In particular,…

Machine Learning · Statistics 2026-04-13 Rohan Hore , Rina Foygel Barber

We derive necessary and sufficient conditions for a group of density matrices to characterize what different people may know about one and the same physical system.

Quantum Physics · Physics 2009-11-07 Todd A. Brun , J. Finkelstein , N. David Mermin

We propose novel methodology for testing equality of model parameters between two high-dimensional populations. The technique is very general and applicable to a wide range of models. The method is based on sample splitting: the data is…

Methodology · Statistics 2013-01-17 Nicolas Städler , Sach Mukherjee