• 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
A randomized coordinate descent method with volume sampling

Rodomanov A., Kropotov D.

SIAM Journal on Optimization. 2020. Vol. 30. No. 3. P. 1878-1904.

ML-assisted versatile approach to Calorimeter R&D

A. Boldyrev, D. Derkach, F. Ratnikov et al.

Journal of Instrumentation. 2020. Vol. 15. P. 1-7.

An accelerated directional derivative method for smooth stochastic convex optimization

Dvurechensky P., Eduard Gorbunov, Gasnikov A.

European Journal of Operational Research. 2021. Vol. 290. No. 2. P. 601-621.

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.

Summer School on Machine Learning in High Energy Physics Took Place

Summer School on Machine Learning in High Energy Physics Took Place

On July 15-30, the Seventh International School on Machine Learning in High Energy Physics (MLHEP) organised by the Laboratory of Methods for Big Data Analysis (LAMBDA), Yandex School of Data Analysis and EPFL (Switzerland) took place.

This year's school attracted 121 participants, including representatives of 70 universities and research centres from Russia (Institute of Astronomy of the Russian Academy of Sciences, Joint Institute for Nuclear Research, Moscow Institute for Physics and Technology), Europe (CERN, Oxford and Cambridge Universities) and the USA (Columbia and Princeton University). For the second time, the school was held online.

As usual, the main topics of the school included machine learning, neural networks, deep and distributed learning, generative models and methods, Bayesian methods and optimisation. This year, guest speakers from outside the school complemented the programme with such topics as:

  • Quantum Computing and Machine Learning (Alexei Fedorov, Russian Quantum Center)
  • Evaluating the Stability of Classifiers (Mike Williams, MIT)
  • Introduction to Simulation-Based Inference Methods (Jakob Macke, University of Tübingen)
  • Applications of simulation-based inference to the physical sciences (Gilles Louppe, University of Liège)
  • Deep transformer architectures for working with sequences (Ekaterina Artemova, HSE University)
  • Using generative models to accelerate the simulation of physical experiments (Lucio Andrelini, University of Bologna)

The organisers and participants shared their impressions of the school:

Ekaterina Trofimova
Research Assistant, Summer School organiser

Like last year, the MLHEP2021 summer school was held online. During two weeks a very busy program of lectures and workshops allowed for quite a deep dive into the world of machine learning. I would like to note students' enthusiasm and desire for personal interaction that flourished during social activities, such as games and coffee-breaks in speed-dating format.

Mikhail Lazarev
Researcher, Summer School participant

Of course, it is impossible to cover everything in a fortnight, but nevertheless, the summer school covered most of the topics connected with machine learning in physics. Each topic was accompanied not only by a lecture but also by a workshop during which algorithms from the lecture were used. This is especially important for beginners in this field. 

From the beginner's viewpoint, the summer school provides a large amount of qualitative information in a short time, and that is a plus. It is also important to note the high level of the teachers and the opportunity to talk to them - they were happy to answer any questions.

Experienced researchers were primarily interested in guest lecturers. The format of the school is also very convenient - if you already know the educational part, you can listen to the lecture and talk to the lecturer. Inconvenient time? A recording of the lecture will be available.

As for me, I've refreshed my knowledge and got to know some new algorithms, which I haven't yet encountered in practice, but with a high probability, I will in the near future. Plus it was nice to apply them to the data from the Large Hadron Collider :)

Vichayanun Wachirapusitanand
Summer School participant

I have been studying machine learning and its applications for several years, yet I did not have a structured knowledge of the field. During my time in this school, I learned several machine learning methods starting from the simplest to the most complicated ones. I also get to see the connection between these methods and how simple techniques add up to elaborate ideas. This school also introduced me to many state-of-the-art neural network designs based on novel ideas that I never imagined possible. I can't wait to get my hands on these sophisticated ideas I learned in this school and apply them in my future work.

Andrey Ustyuzhanin
Laboratory Head, Summer School organiser

We are delighted that the school's programme harmoniously combines talks by machine learning experts on current approaches and methods of data analysis with talks by leading scientists on current challenges and problems in various fields of physics.