• 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 Methodical and Educational Work — Ilya Samonenko

 

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'). 

Events
Feb 22 – Feb 23
Регистрация открыта 
Mar 21 – Mar 23
Papers Submission Deadline: 15 January 2019 
Jun 12 – Jun 14
submission: Friday, 01 February 2019, notification: Friday, 15 February 2019 
Aug 26 – Aug 30
Registration and Poster Submission deadline — April 1, 2019 
Article
Ontology-Mediated Queries: Combined Complexity and Succinctness of Rewritings via Circuit Complexity

Bienvenu M., Kikot S., Kontchakov R. et al.

Journal of the ACM. 2018. Vol. 65. No. 5. P. 28:1-28:51.

Article
Randomized Block Cubic Newton Method
In press

Doikov Nikita, Richtarik P.

Proceedings of Machine Learning Research. 2018. No. 80. P. 1290-1298.

Article
Particle-identification techniques and performance at LHCb in Run 2
In press

Hushchyn M., Chekalina V.

Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment. 2018. P. 1-2.

Article
Observational evidence in favor of scale free evolution of sunspot groups

Shapoval A., Le Mouël J., Shnirman M. et al.

Astronomy and Astrophysics. 2018. Vol. 618. P. A183-1-A183-13.

Faculty Colloquium: On empirical risk minimization and its variants for statistical learning. Speaker: Quentin Paris, HSE

Event ended

January 23, 18:10 – 19:30 

Quentin Paris, HSE 

On empirical risk minimization and its variants for statistical learning

In this talk, we review fundamental principles of empirical risk minimization and its performance guarantees for statistical learning. We discuss the close interaction with the field of empirical processes and the connection to Vapnik–Chervonenkis combinatorics (including the notion of combinatorial dimension). We present the best known theoretical guarantees for the prediction error of empirical risk minimizers, discuss the limitations of the method, and mention some recent contributions.

Colloquium

Venue:

Moscow, Kochnovsky pr.,3, room 205, 18:10 
Everyone interested is welcome to attend. 
If you need a pass to HSE, please contact computerscience@hse.ru