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

109028, Moscow,
11, Pokrovsky boulevard

Phone: +7 (495) 531-00-00 *27254

Email: computerscience@hse.ru


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
Working paper
Robust covariance estimation under L_4-L_2 norm equivalence

Mendelson S., Zhivotovskiy N.

math. arxive. Cornell University, 2018

An accelerated directional derivative method for smooth stochastic convex optimization
In press

Dvurechensky P., Eduard Gorbunov, Gasnikov A.

European Journal of Operational Research. 2020. P. 1-21.

Random hypergraphs and property B

Shabanov D. A., Kozik J., Duraj L.

European Journal of Combinatorics. 2021. Vol. 91. P. 1-11.

Book chapter
On pattern setups and pattern multistructures

Kuznetsov S., Kaytoue M., Belfodil A.

In bk.: International Journal of General Systems. Iss. 49. 2020. P. 271-285.

Book chapter
Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise

Kaledin M., Moulines E., Naumov A. et al.

In bk.: Proceedings of Machine Learning Research. Vol. 125: Proceedings of Thirty Third Conference on Learning Theory. 2020. P. 2144-2203.

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.

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