58 citations
- Moscow Institute of Physics and TechnologyRU6 papers
- Fraunhofer Institute for Open Communication SystemsDE2 papers
- Lomonosov Moscow State UniversityRU2 papers
- National Research University Higher School of EconomicsRU2 papers
- Russian Academy of SciencesRU2 papers
- 3rd Central Research Institute of the Russian Defence MinistryRU1 paper
- Academy of Federal Security Guard Service of Russian FederationRU1 paper
- Ericsson (Hungary)HU1 paper
- Ericsson (Sweden)SE1 paper
- European Telecommunications Standards InstituteFR1 paper
- Federal Protective ServiceRU1 paper
- Humboldt-Universität zu BerlinDE1 paper
7 papers · 1 filter
Control of Overfitting with Physics
Sergei V. Kozyrev, Ilya A Lopatin, Alexander N Pechen
While there are many works on the applications of machine learning, not so many of them are trying to understand the theoretical justifications to explain their efficiency. In this…
MamT: Multi-view Attention Networks for Mammography Cancer Classification
Alisher Ibragimov, Sofya Senotrusova, Arsenii Litvinov +3
In this study, we introduce a novel method, called MamT, which is used for simultaneous analysis of four mammography images. A decision is made based on one image of a breast,…
Method with Batching for Stochastic Finite-Sum Variational Inequalities in Non-Euclidean Setting
Alexander Pichugin, Maksim Pechin, Aleksandr Beznosikov +2
Variational inequalities are a universal optimization paradigm that incorporate classical minimization and saddle point problems. Nowadays more and more tasks require to consider s…
Gradient-free algorithm for saddle point problems under overparametrization
Ekaterina Statkevich, Sofiya Bondar, Darina Dvinskikh +2
This paper focuses on solving a stochastic saddle point problem (SPP) under an overparameterized regime for the case, when the gradient computation is impractical. As an intermedia…
Random Graph Modeling: A survey of the concepts
Mikhail Drobyshevskiy, Denis Turdakov
Random graph (RG) models play a central role in the complex networks analysis. They help to understand, control, and predict phenomena occurring, for instance, in social networks,…
Collecting Influencers: A Comparative Study of Online Network Crawlers
Mikhail Drobyshevskiy, Denis Aivazov, Denis Turdakov +3
Online network crawling tasks require a lot of efforts for the researchers to collect the data. One of them is identification of important nodes, which has many applications starti…