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

Dean — Ivan Arzhantsev

 

First Deputy Dean — Tamara Voznesenskaya

 

Deputy Dean for Research and International Relations — Sergei Obiedkov

 

Deputy Dean for Development, Finance and Administration — Irina Plisetskaya

Phone: +7 (495) 772-95-90 * 12332

computerscience@hse.ru

125319, Moscow, 3 Kochnovsky Proezd (near metro station 'Aeroport'). 

Article
Linear switched dynamical systems on graphs
In print

Protasov V. Y., Cicone A., Guglielmi N.

Nonlinear Analysis: Hybrid Systems. 2018. Vol. 29. P. 165-186.

Article
Final Results of the OPERA Experiment on ντ Appearance in the CNGS Neutrino Beam

Ustyuzhanin A.

Physical Review Letters. 2018. Vol. 120. No. 21. P. 211801-1-211801-7.

Article
Qualitative Judgement of Research Impact: Domain Taxonomy as a Fundamental Framework for Judgement of the Quality of Research

Murtagh F., Orlov M. A., Mirkin B.

Journal of Classification. 2018. Vol. 35. No. 1. P. 5-28.

Article
Predictive Model for the Bottomhole Pressure based on Machine Learning
In print

Spesivtsev P., Sinkov K., Sofronov I. et al.

Journal of Petroleum Science and Engineering. 2018.

Article
New and old results on spherical varieties via moduli theory

Roman Avdeev, Cupit-Foutou S.

Advances in Mathematics. 2018. Vol. 328. P. 1299-1352.

Colloquium: Perturbed Proximal Gradient Algorithms. Speaker: Eric Moulines (École Polytechnique)

Event ended

February 22, 18:10 – 19:30, room 317

Eric Moulines (École Polytechnique, France) 

Perturbed Proximal Gradient Algorithms

We study a version of the proximal gradient algorithm for which the gradient is intractable and is approximated by Monte Carlo methods (and in particular Markov Chain Monte Carlo). We derive conditions on the step size and the Monte Carlo batch size under which convergence is guaranteed: both increasing batch size and constant batch size are considered. We also derive non-asymptotic bounds for an averaged version. Our results cover both the cases of biased and unbiased Monte Carlo approximation. To support our findings, we discuss the inference of a sparse generalized linear model with random effect and the problem of learning the edge structure and parameters of sparse undirected graphical models.

Venue: Moscow, Kochnovsky proezd, 3, room 317, 18:10

Registration is open. 

Registration