• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Educational Programme
Final Grade
Year of Graduation
Dmitriy Salnikov
Statistical Fairness through Optimal Transport Theory
Statistical Learning Theory
(Master’s programme)
Machine learning algorithms are heavily influenced by the data which

is used to fit them. If the data collection process is incorrect, this

may potentially lead to overfitting and as a result the undesirable

treatment with respect to a given groups.

The solution was presented to mitigate the impact of this while

sacrificing as little predictive performance as possible by

effectively leveraging the optimal transport theory. However, the

algorithm is cubic with respect to the input size, which limits its

application. We consider computationally efficient approximate

algorithms and empirically show that the algorithm's performance is

not hindered by this, which suggests that such algorithms can be

applied in practice. Moreover, we suggest an algorithm that adjusts

the solution for out of sample data.

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