On the Acceleration of SGD for Mixture Separation Learning

Student: Matiushin Leonid

Supervisor: Andrey Ustyuzhanin

Educational Programme: Mathematics (Bachelor)

Year of Graduation: 2018

In this work, we consider a binary classification problem in the setting of mixture of two probability distributions, such as they are similar on the most part of their support. We present a modification of importance sampling method for stochastic gradient descent. We provide empirical and theoretical analysis and conclude that our approach is rather more effective than classical stochastic gradient descent.

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