Instytut Podstawowych Problemów Techniki
Polskiej Akademii Nauk

Partnerzy

N. Beerenwinkel


Prace konferencyjne
1.  Czyż P., Grabowski F., Vogt J., Beerenwinkel N., Marx A., Beyond Normal: On the Evaluation of Mutual Information Estimators, NeurIPS 2023, Advances in Neural Information Processing Systems, 2023-12-10/12-16, New Orleans (US), pp.1-34, 2023

Streszczenie:
Mutual information is a general statistical dependency measure which has found applications in representation learning, causality, domain generalization and computational biology. However, mutual information estimators are typically evaluated on simple families of probability distributions, namely multivariate normal distribution and selected distributions with one-dimensional random variables. In this paper, we show how to construct a diverse family of distributions with known ground-truth mutual information and propose a language-independent benchmarking platform for mutual information estimators. We discuss the general applicability and limitations of classical and neural estimators in settings involving high dimensions, sparse interactions, long-tailed distributions, and high mutual information. Finally, we provide guidelines for practitioners on how to select appropriate estimator adapted to the difficulty of problem considered and issues one needs to consider when applying an estimator to a new data set.

Afiliacje autorów:
Czyż P. - University of Oxford (GB)
Grabowski F. - IPPT PAN
Vogt J. - inna afiliacja
Beerenwinkel N. - inna afiliacja
Marx A. - inna afiliacja

Kategoria A Plus

IPPT PAN

logo ippt            ul. Pawińskiego 5B, 02-106 Warszawa
  +48 22 826 12 81 (centrala)
  +48 22 826 98 15
 

Znajdź nas

mapka
© Instytut Podstawowych Problemów Techniki Polskiej Akademii Nauk 2024