English
Related papers

Related papers: $\ell_p$ Testing and Learning of Discrete Distribu…

200 papers

Estimating the support size of a distribution is a well-studied problem in statistics. Motivated by the fact that this problem is highly non-robust (as small perturbations in the distributions can drastically affect the support size) and…

Data Structures and Algorithms · Computer Science 2022-11-22 Shyam Narayanan , Jakub Tětek

In this paper we obtain improved iteration complexities for solving $\ell_p$ regression. We provide methods which given any full-rank $\mathbf{A} \in \mathbb{R}^{n \times d}$ with $n \geq d$, $b \in \mathbb{R}^n$, and $p \geq 2$ solve…

Data Structures and Algorithms · Computer Science 2021-11-11 Arun Jambulapati , Yang P. Liu , Aaron Sidford

In the distributed monitoring model, a data stream over a universe of size $n$ is distributed over $k$ servers, who must continuously provide certain statistics of the overall dataset, while minimizing communication with a central…

Data Structures and Algorithms · Computer Science 2025-10-28 Honghao Lin , Zhao Song , David P. Woodruff , Shenghao Xie , Samson Zhou

This paper studies the complexity of estimating Renyi divergences of discrete distributions: $p$ observed from samples and the baseline distribution $q$ known \emph{a priori}. Extending the results of Acharya et al. (SODA'15) on estimating…

Information Theory · Computer Science 2017-02-09 Maciej Skorski

A recent model for property testing of probability distributions (Chakraborty et al., ITCS 2013, Canonne et al., SICOMP 2015) enables tremendous savings in the sample complexity of testing algorithms, by allowing them to condition the…

Data Structures and Algorithms · Computer Science 2018-12-10 Jayadev Acharya , Clément L. Canonne , Gautam Kamath

We analyze the problem of discrete distribution estimation under $\ell_1$ loss. We provide non-asymptotic upper and lower bounds on the maximum risk of the empirical distribution (the maximum likelihood estimator), and the minimax risk in…

Information Theory · Computer Science 2015-12-31 Yanjun Han , Jiantao Jiao , Tsachy Weissman

We consider inference on the first principal direction of a $p$-variate elliptical distribution. We do so in challenging double asymptotic scenarios for which this direction eventually fails to be identifiable. In order to achieve…

Statistics Theory · Mathematics 2019-08-30 Davy Paindaveine , Julien Remy , Thomas Verdebout

Learning from Label Proportions (LLP) is a learning setting, where the training data is provided in groups, or "bags", and only the proportion of each class in each bag is known. The task is to learn a model to predict the class labels of…

Machine Learning · Statistics 2015-02-13 Felix X. Yu , Krzysztof Choromanski , Sanjiv Kumar , Tony Jebara , Shih-Fu Chang

We consider the detection problem of correlations in a $p$-dimensional Gaussian vector, when we observe $n$ independent, identically distributed random vectors, for $n$ and $p$ large. We assume that the covariance matrix varies in some…

Statistics Theory · Mathematics 2016-01-27 Cristina Butucea , Rania Zgheib

We consider learning in an adversarial environment, where an $\varepsilon$-fraction of samples from a distribution $P$ are arbitrarily modified (global corruptions) and the remaining perturbations have average magnitude bounded by $\rho$…

Machine Learning · Computer Science 2024-06-26 Sloan Nietert , Ziv Goldfeld , Soroosh Shafiee

We give improved algorithms for the $\ell_{p}$-regression problem, $\min_{x} \|x\|_{p}$ such that $A x=b,$ for all $p \in (1,2) \cup (2,\infty).$ Our algorithms obtain a high accuracy solution in $\tilde{O}_{p}(m^{\frac{|p-2|}{2p + |p-2|}})…

Data Structures and Algorithms · Computer Science 2024-12-20 Deeksha Adil , Rasmus Kyng , Richard Peng , Sushant Sachdeva

Distributional assumptions have been shown to be necessary for the robust learnability of concept classes when considering the exact-in-the-ball robust risk and access to random examples by Gourdeau et al. (2019). In this paper, we study…

Machine Learning · Computer Science 2023-07-21 Pascale Gourdeau , Varun Kanade , Marta Kwiatkowska , James Worrell

The measurement error with normal distribution is universal in applications. Generally, smaller measurement error requires better instrument and higher test cost. In decision making based on attribute values of objects, we shall select an…

Artificial Intelligence · Computer Science 2013-06-04 Hong Zhao , Fan Min , William Zhu

This paper addresses a fundamental problem in random variate generation: given access to a random source that emits a stream of independent fair bits, what is the most accurate and entropy-efficient algorithm for sampling from a discrete…

Data Structures and Algorithms · Computer Science 2020-03-10 Feras A. Saad , Cameron E. Freer , Martin C. Rinard , Vikash K. Mansinghka

In this paper, we consider the related problems of multicalibration -- a multigroup fairness notion and omniprediction -- a simultaneous loss minimization paradigm, both in the distributional and online settings. The recent work of Garg et…

Machine Learning · Computer Science 2025-05-29 Haipeng Luo , Spandan Senapati , Vatsal Sharan

The algorithmic theory of randomness is well developed when the underlying space is the set of finite or infinite sequences and the underlying probability distribution is the uniform distribution or a computable distribution. These…

Computational Complexity · Computer Science 2016-08-31 Peter Gacs

Methods of performing anomaly detection on high-dimensional data sets are needed, since algorithms which are trained on data are only expected to perform well on data that is similar to the training data. There are theoretical results on…

Machine Learning · Computer Science 2020-11-13 Forrest Laine , Claire Tomlin

Machine learning theory has mostly focused on generalization to samples from the same distribution as the training data. Whereas a better understanding of generalization beyond the training distribution where the observed distribution…

Machine Learning · Statistics 2019-05-29 Matias Vera , Pablo Piantanida , Leonardo Rey Vega

We study the $L_p$-discrepancy of random point sets in high dimensions, with emphasis on small values of $p$. Although the classical $L_p$-discrepancy suffers from the curse of dimensionality for all $p \in (1,\infty)$, the gap between…

Numerical Analysis · Mathematics 2025-12-10 Erich Novak , Friedrich Pillichshammer

We study the problems of learning and testing junta distributions on $\{-1,1\}^n$ with respect to the uniform distribution, where a distribution $p$ is a $k$-junta if its probability mass function $p(x)$ depends on a subset of at most $k$…

Data Structures and Algorithms · Computer Science 2020-04-28 Xi Chen , Rajesh Jayaram , Amit Levi , Erik Waingarten