Learning probability by comparison

Taisuke Sato

Learning probability by comparison

Taisuke Sato ;

Proceedings of The 3rd International Workshop on Advanced Methodologies for Bayesian Networks, PMLR 73:5-5, 2017.

Abstract

Learning probability by probabilistic modeling is a major task in statistical machine learning and it has traditionally been supported by maximum likelihood estimation applied to generative models or by a local maximizer applied to discriminative models. In this talk, we introduce a third approach, an innovative one that learns probability by comparing probabilistic events. In our approach, we give the ranking of probabilistic events and the system learns a probability distribution so that the ranking is well respected. We implemented this approach in PRISM, a logic-based probabilistic programming language, and conducted learning experiments with real data for models described by PRISM programs.

Related Material

Download PDF

@InProceedings{pmlr-v73-sato17a, title = {Learning probability by comparison}, author = {Taisuke Sato}, booktitle = {Proceedings of The 3rd International Workshop on Advanced Methodologies for Bayesian Networks}, pages = {5--5}, year = {2017}, editor = {Antti Hyttinen and Joe Suzuki and Brandon Malone}, volume = {73}, series = {Proceedings of Machine Learning Research}, address = {}, month = {20--22 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v73/sato17a/sato17a.pdf}, url = {http://proceedings.mlr.press/v73/sato17a.html}, abstract = {Learning probability by probabilistic modeling is a major task in statistical machine learning and it has traditionally been supported by maximum likelihood estimation applied to generative models or by a local maximizer applied to discriminative models. In this talk, we introduce a third approach, an innovative one that learns probability by comparing probabilistic events. In our approach, we give the ranking of probabilistic events and the system learns a probability distribution so that the ranking is well respected. We implemented this approach in PRISM, a logic-based probabilistic programming language, and conducted learning experiments with real data for models described by PRISM programs.} }

%0 Conference Paper %T Learning probability by comparison %A Taisuke Sato %B Proceedings of The 3rd International Workshop on Advanced Methodologies for Bayesian Networks %C Proceedings of Machine Learning Research %D 2017 %E Antti Hyttinen %E Joe Suzuki %E Brandon Malone %F pmlr-v73-sato17a %I PMLR %J Proceedings of Machine Learning Research %P 5--5 %U http://proceedings.mlr.press %V 73 %W PMLR %X Learning probability by probabilistic modeling is a major task in statistical machine learning and it has traditionally been supported by maximum likelihood estimation applied to generative models or by a local maximizer applied to discriminative models. In this talk, we introduce a third approach, an innovative one that learns probability by comparing probabilistic events. In our approach, we give the ranking of probabilistic events and the system learns a probability distribution so that the ranking is well respected. We implemented this approach in PRISM, a logic-based probabilistic programming language, and conducted learning experiments with real data for models described by PRISM programs.