815 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- I. Oseledets26 · h 51
- A. Bogatyrev13 · h 10
- K. Metlov11 · h 14
- S. Matveev4 profiles10 · h 9
- A. Smirnov4 profiles8 · h 24
- M. Rakhuba2 profiles7 · h 6
- N. Brilliantov2 profiles6 · h 30
- P. Krapivsky2 profiles6 · h 45
- Alexander Osinsky2 profiles5 · h 12
- E. Tyrtyshnikov5 · h 32
- P. Berloff5 · h 33
- S. Budzinskiy5 · h 6
- Russian Academy of SciencesRU62 papers
- Skolkovo Institute of Science and TechnologyRU35 papers
- Lomonosov Moscow State UniversityRU22 papers
- Moscow Institute of Physics and TechnologyRU13 papers
- Donetsk Institute for Physics and Engineering named after O.O. GalkinUA7 papers
- Imperial College LondonGB6 papers
- Boston UniversityUS5 papers
- National Research University Higher School of EconomicsRU5 papers
- University of LeicesterGB5 papers
- University of HoustonUS4 papers
- University of ReadingGB4 papers
- ETH ZurichCH3 papers
4 papers · 1 filter
Variational Bayesian inference for CP tensor completion with side information
Stanislav Budzinskiy, Nikolai Zamarashkin
We propose a message passing algorithm, based on variational Bayesian inference, for low-rank tensor completion with automatic rank determination in the canonical polyadic format w…
Active Subspace of Neural Networks: Structural Analysis and Universal Attacks
Chunfeng Cui, Kaiqi Zhang, Talgat Daulbaev +3
Active subspace is a model reduction method widely used in the uncertainty quantification community. In this paper, we propose analyzing the internal structure and vulnerability an…
Empirical study of extreme overfitting points of neural networks
Daniil Merkulov, Ivan Oseledets
In this paper we propose a method of obtaining points of extreme overfitting - parameters of modern neural networks, at which they demonstrate close to 100 % training accuracy, sim…
Tensorizing Neural Networks
Alexander Novikov, Dmitry Podoprikhin, Anton Osokin +1
Deep neural networks currently demonstrate state-of-the-art performance in several domains. At the same time, models of this class are very demanding in terms of computational reso…