Approximation of the Logistic Function by the Normal CDF in the Stochastic Metropolis-Hastings

Student: Chernov Andrey

Educational Programme: Data Science (Master)

Year of Graduation: 2021

The state of the art models have intractable likelihood. So we can not compute posterior distribution over weights analytically, but using Markov chain monte carlo framework (MCMC) we can approximate it. The most popular MCMC methods use Metropolis-Hastings (MH) acceptance test to get unbiased estimator of the posterior distribution. MH acceptance test re- quires iterate over full dataset on each step. Thus, the training procedure of the MCMC methods is time-consuming. In this paper we will propose subsampling MH acceptance test.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses