• 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 finance and administration - Irina Plisetskaya

 

Dean's office
 

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

computerscience@hse.ru

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

Book chapter
GANs for Biological Image Synthesis

Osokin A., Chessel A., Carazo Salas R. E. et al.

In bk.: Proceedings of the IEEE International Conference on Computer Vision (ICCV 2017). Venice: IEEE, 2017. P. 2252-2261.

Article
The Second Term in the Asymptotics for the Number of Points Moving Along a Metric Graph

Vsevolod L. Chernyshev, Tolchennikov A. A.

Regular and Chaotic Dynamics. 2017. Vol. 22. No. 8. P. 937-948.

Article
A Conditional Information Inequality and its Combinatorial Applications

Vereshchagin N., Kaced T., Romashchenko A.

IEEE Transactions on Information Theory. 2018. Vol. 64. No. 5. P. 3610-3615.

Article
Dual subgradient method with averaging for optimal resource allocation
In print

Nesterov Y., Shikhman V.

European Journal of Operational Research. 2018. P. 1-10.

Article
Finite sample properties of the mean occupancy counts and probabilities
In print

Decrouez G. G., Grabchak M., Paris Q.

Bernoulli: a journal of mathematical statistics and probability. 2018. Vol. 24. No. 3. P. 1910-1941.

Colloquium: Learning on networks of distributions for discrete data. Speaker: Wray Buntine, Monash University

Event ended

I will motivate the talk by reviewing some state of the art models for problems like matrix factorisation models for link prediction and tweet clustering. Then I will review the classes of distributions that can be strung together in networks to generate discrete data. This allows a rich class of models that, in its simplest form, covers things like Poisson matrix factorisation, Latent Dirichlet allocation, and Stochastic block models, but, more generally, covers complex hierarchical models on network and text data. The distributions covered include so-called non-parametric distributions such as the Gamma process. Accompanying these are a set of collapsing and augmentation techniques that are used to generate fast Gibbs samplers for many models in this class. To complete this picture, turning complex network models into fast Gibbs samplers, I will illustrate our recent methods of doing matrix factorisation with side information (e.g., GloVe word embeddings), done for link prediction, for instance, for citation networks.

Venue:
Moscow, Kochnovsky pr.,3, room 317, 18:10 

Everyone interested is welcome to attend.

If you need a pass to HSE, please contact computerscience@hse.ru