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

International Laboratory of Stochastic Algorithms and High-Dimensional Inference

Publications
Publications
Article
Low-rank diffusion matrix estimation for high-dimensional time-changed Levy processes

Belomestny D., Trabs M.

Annales de l'institut Henri Poincare (B) Probability and Statistics. 2018. Vol. 54. No. 3. P. 1583-1621.

Book chapter
Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn’s Algorithm

Dvurechensky P., Gasnikov A., Kroshnin A.

In bk.: Proceedings of Machine Learning Research. Vol. 80: Proceedings of the International Conference on Machine Learning (ICML 2018). PMLR, 2018. P. 1367-1376.

Working paper
Mass transportation functionals on the sphere with applications to the logarithmic Minkowski problem

Kolesnikov A.

math. arxive. Cornell University, 2018

The International Laboratory of Stochastic Algorithms and High-Dimensional Inference was created in April 2018 and is part of the Faculty of Computer Science at HSE.

Russian and international researchers work at the laboratory at the intersection of numerous mathematical disciplines, including modern statistics, optimisation, probability theory and theory of computation. Its main aim is to develop new probability and statistical approaches to current problems in the field of data analysis.

8

October 09

The HSE Faculty of Computer Science has launched the International Laboratory of Stochastic Algorithms and High-Dimensional Inference (HDI Lab). The Lab’s Academic Supervisor,Eric Moulines, and Chief Research Fellow, Vladimir Spokoiny, spoke to us about the fundamental and applied aspects of research performed by the laboratory, their relations with machine learning, and Russian-French academic ties.

September 10

On September 10 Steve Oudot, Professor at Ecole Polytechnique and Researcher at INRIA, gave a mini-course "Statistics and Learning with topological descriptors".

July 19

12th International Vilnius Conference on Probability Theory and Mathematical Statistics and 2018 IMS Annual Meeting on Probability and Statistics took place in Vilnius (Lithuania) on July 2-6. This is one of the world's leading conferences in the field of modern probability theory and mathematical statistics, which is held every four years since 1973. This year over 200 works were presented at the event and 500 participants from all over the globe attended it.

July 18

On 19 July at 11 am an extraordinary meeting of Structural Learning Seminar was held on the Faculty of Computer Science.

June 05

On May 17 and 24 Professor at the University of Minnesota and Chief Research Fellow of HDI Lab Sergey Bobkov gave a mini-course on "Strong probability distances and limit theorems".

May 02

Team of researchers of the HSE International Laboratory of Stochastic Algorithms and High-Dimensional Inference was announced as a winner of the Russian Science Foundation Grant Competition to support fundamental and exploratory scientific research conducted by individual scientific groups and was awarded three-year grant for implementation of the project "Analysis of high dimensional random objects with applications to large scale data processing" (RSF №18-11-00132).

March 15

On February 23 and 24, the Institute for Information Transmission Problems of the Russian Academy of Sciences hosted the first international mini-conference entitled ‘New frontiers in high-dimensional probability and statistics’. The event was attended by Russian and international researchers in the field of statistical methods of analysis of multidimensional data and modern stochastic algorithms. The conference was hosted by HSE, the Institute for Information Transmission Problems of the RAS and Skoltech. Organisers included HSE Faculty of Computer Science staff, Vladimir Spokoiny, Alexey Naumov, Denis Belomestny and Quentin Paris.

February 22

On February 22 at the Faculty of Computer Science Colloquium Academic Supervisor of Laboratory Eric Moulines gave a talk «Perturbed Proximal Gradient Algorithms».