English
Related papers

Related papers: On the Upper Limit of Separability

200 papers

Discrimination in machine learning often arises along multiple dimensions (a.k.a. protected attributes); it is then desirable to ensure \emph{intersectional fairness} -- i.e., that no subgroup is discriminated against. It is known that…

Machine Learning · Statistics 2023-06-27 Mathieu Molina , Patrick Loiseau

In this paper we propose a Bayesian answer to testing problems when the hypotheses are not well separated. The idea of the method is to study the posterior distribution of a discrepancy measure between the parameter and the model we want to…

Statistics Theory · Mathematics 2017-06-28 Jean-Bernard Salomond

In this work, we give a novel general approach for distribution testing. We describe two techniques: our first technique gives sample-optimal testers, while our second technique gives matching sample lower bounds. As a consequence, we…

Data Structures and Algorithms · Computer Science 2016-05-10 Ilias Diakonikolas , Daniel M. Kane

We study a hypothesis testing problem in which data is compressed distributively and sent to a detector that seeks to decide between two possible distributions for the data. The aim is to characterize all achievable encoding rates and…

Information Theory · Computer Science 2011-02-01 Md. Saifur Rahman , Aaron B. Wagner

The ability to compute the exact divergence between two high-dimensional distributions is useful in many applications but doing so naively is intractable. Computing the alpha-beta divergence -- a family of divergences that includes the…

Machine Learning · Computer Science 2023-10-17 Loong Kuan Lee , Geoffrey I. Webb , Daniel F. Schmidt , Nico Piatkowski

Segregation is a multi-scale phenomenon that requires careful measurement. A segregation index implicitly defines how the demographic compositions of locations are compared. We identify two properties -- mean-minimisation and invariance --…

Physics and Society · Physics 2026-03-17 Rohit Sahasrabuddhe , Renaud Lambiotte

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

Retrieving classical information encoded in optical modes is at the heart of many quantum information processing tasks, especially in the field of quantum communication and sensing. Yet, despite its importance, the fundamental limits of…

Quantum Physics · Physics 2021-05-11 Ignatius William Primaatmaja , Asaph Ho , Valerio Scarani

Heterogeneous datasets emerge in various machine learning and optimization applications that feature different input sources, types or formats. Most models or methods do not natively tackle heterogeneity. Hence, such datasets are often…

Machine Learning · Statistics 2025-08-25 Edward Hallé-Hannan , Charles Audet , Youssef Diouane , Sébastien Le Digabel , Paul Saves

Models often need to be constrained to a certain size for them to be considered interpretable. For example, a decision tree of depth 5 is much easier to understand than one of depth 50. Limiting model size, however, often reduces accuracy.…

Machine Learning · Computer Science 2020-07-02 Abhishek Ghose , Balaraman Ravindran

Bayesian analysis plays a crucial role in estimating distribution of unknown parameters for given data and model. Due to the curse of dimensionality, it becomes difficult for high-dimensional problems, especially when multiple modes exist.…

Methodology · Statistics 2025-07-18 Zihan Liao , Binbin Li , Hua-Ping Wan

Finding the underlying probability distributions of a set of observed sequences under the constraint that each sequence is generated i.i.d by a distinct distribution is considered. The number of distributions, and hence the number of…

Information Theory · Computer Science 2018-10-16 Sara Shahi , Daniela Tuninetti , Natasha Devroye

Motivated by data-rich experiments in transcriptional regulation and sensory neuroscience, we consider the following general problem in statistical inference. When exposed to a high-dimensional signal S, a system of interest computes a…

Quantitative Methods · Quantitative Biology 2013-12-16 Justin B. Kinney , Gurinder S. Atwal

Deep learning systems have been reported to acheive state-of-the-art performances in many applications, and one of the keys for achieving this is the existence of well trained classifiers on benchmark datasets which can be used as backbone…

Machine Learning · Computer Science 2022-10-04 Jirong Yi , Qiaosheng Zhang , Zhen Chen , Qiao Liu , Wei Shao

We introduce the Mutual Information Machine (MIM), a novel formulation of representation learning, using a joint distribution over the observations and latent state in an encoder/decoder framework. Our key principles are symmetry and mutual…

Machine Learning · Statistics 2019-10-10 Micha Livne , Kevin Swersky , David J. Fleet

We consider a multi-object detection problem over a sensor network (SNET) with limited range multi-modal sensors. Limited range sensing environment arises in a sensing field prone to signal attenuation and path losses. The general problem…

Information Theory · Computer Science 2008-09-12 E. Ermis , V. Saligrama

We analyse the splitting algorithm performance in the estimation of rare event probabilities and this in a discrete multidimensional framework. For this we assume that each threshold is partitioned into disjoint subsets and the probability…

Probability · Mathematics 2016-10-10 Agnès Lagnoux , Pascal Lezaud

In the uniformity testing task, an algorithm is provided with samples from an unknown probability distribution over a (known) finite domain, and must decide whether it is the uniform distribution, or, alternatively, if its total variation…

Data Structures and Algorithms · Computer Science 2025-08-05 Guy Blanc , Clément L. Canonne , Erik Waingarten

The Kullback-Leibler divergence, the Kullback-Leibler variation, and the Bernstein "norm" are used to quantify discrepancies among probability distributions in likelihood models such as nonparametric maximum likelihood and nonparametric…

Statistics Theory · Mathematics 2026-01-27 Tetsuya Kaji

As predictive algorithms grow in popularity, using the same dataset to both train and test a new model has become routine across research, policy, and industry. Sample-splitting attains valid inference on model properties by using separate…

Econometrics · Economics 2025-11-27 Bruno Fava