慶應義塾大学 理工学部 数理科学科

理研AIPセミナー

タイトル Description of a normalizing constant by Kirillov character formula
開催日時 2019年5月9日 13:00 - 14:00 + 30 min
主催者
講演者 Koichi Tojo氏
場所 Yagami campus, Keio Univ.
Building 14, Room 631A/B
内容 Parametric models are important theoretically and practically to estimate a true distribution in the field of machine learning. We can obtain a parametric model by normalizing a family of parameterized functions on a sample space. However, in general, it is difficult to calculate the normalizing constant.
Recently, F. Barbaresco introduced a method to describe the normalizing constant of the Gibbs density on Poincaré disk by Kirillov character formula, which has been actively studied in the field of representation theory.
In this talk, we will give an overview of the method and consider its application.
資料
URL