Sampling from Arbitrary Functions via PSD Models

Ulysse Marteau-Ferey, Francis Bach, Alessandro Rudi
Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:2823-2861, 2022.

Abstract

In many areas of applied statistics and machine learning, generating an arbitrary number of inde- pendent and identically distributed (i.i.d.) samples from a given distribution is a key task. When the distribution is known only through evaluations of the density, current methods either scale badly with the dimension or require very involved implemen- tations. Instead, we take a two-step approach by first modeling the probability distribution and then sampling from that model. We use the recently introduced class of positive semi-definite (PSD) models which have been shown to be e

Cite this Paper

BibTeX
@InProceedings{pmlr-v151-marteau-ferey22a, title = { Sampling from Arbitrary Functions via PSD Models }, author = {Marteau-Ferey, Ulysse and Bach, Francis and Rudi, Alessandro}, booktitle = {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics}, pages = {2823--2861}, year = {2022}, editor = {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel}, volume = {151}, series = {Proceedings of Machine Learning Research}, month = {28--30 Mar}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v151/marteau-ferey22a/marteau-ferey22a.pdf}, url = {https://proceedings.mlr.press/v151/marteau-ferey22a.html}, abstract = { In many areas of applied statistics and machine learning, generating an arbitrary number of inde- pendent and identically distributed (i.i.d.) samples from a given distribution is a key task. When the distribution is known only through evaluations of the density, current methods either scale badly with the dimension or require very involved implemen- tations. Instead, we take a two-step approach by first modeling the probability distribution and then sampling from that model. We use the recently introduced class of positive semi-definite (PSD) models which have been shown to be e } }
Endnote
%0 Conference Paper %T Sampling from Arbitrary Functions via PSD Models %A Ulysse Marteau-Ferey %A Francis Bach %A Alessandro Rudi %B Proceedings of The 25th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2022 %E Gustau Camps-Valls %E Francisco J. R. Ruiz %E Isabel Valera %F pmlr-v151-marteau-ferey22a %I PMLR %P 2823--2861 %U https://proceedings.mlr.press/v151/marteau-ferey22a.html %V 151 %X In many areas of applied statistics and machine learning, generating an arbitrary number of inde- pendent and identically distributed (i.i.d.) samples from a given distribution is a key task. When the distribution is known only through evaluations of the density, current methods either scale badly with the dimension or require very involved implemen- tations. Instead, we take a two-step approach by first modeling the probability distribution and then sampling from that model. We use the recently introduced class of positive semi-definite (PSD) models which have been shown to be e
APA
Marteau-Ferey, U., Bach, F. & Rudi, A.. (2022). Sampling from Arbitrary Functions via PSD Models . Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 151:2823-2861 Available from https://proceedings.mlr.press/v151/marteau-ferey22a.html.

Related Material