Learning to Rank with Variational Optimization

Student: Ponamareva Irina

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2020

Learning to rank is a ubiquitous problem that appears in recommender systems, search engines, and other applications. However, all of the existing methods currently optimize some surrogate functions instead of the target metric, due to optimization challenges. This work attempts to solve the learning to rank problem via variational optimization of the target metric, normalized discounted cumulative gain, a widely used measure of ranking quality. We will use an approach analogous to the Gumbel-Max trick for categorical distributions to optimize normalize discounted cumulative gain directly and show the applicability of this method for real-life ranking problems.

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