School 1-2 November
HSE University invites you to join an autumn school on machine learning aimed at undergraduate/graduate students and young postdoctoral fellows from pure and applied mathematics. This intense two-day event will consist of 4 interdisciplinary mini-courses.
Conference 3 November
The third day is conference. It will be very similar to an A* level conference: short papers (15 min), long poster session.
Tentative list of speakers
Skoltech, AIRI
HSE University
Skoltech, AIRI
HSE University, AIRI
HSE University, AIRI
MIPT
AIRI
MIPT
HSE University
HSE University
Skoltech
HSE University
Lomonosov MSU
HSE University
INR RAS
HSE University
Skoltech
Innopolis University
Skoltech, AIRI
Skoltech
HSE University
ISP RAS, MSU
HSE University
MIPT
HSE University, Skoltech
Skoltech
Skoltech
Skoltech
HSE University
Skoltech
HSE University
Yandex & HSE
HSE University
HSE University
HSE University
HSE University
Lomonosov MSU
Skoltech
HSE University
Skoltech
This school is supported by the RSF grant N19-71-30020 "Applications of probabilistic artificial neural generative models in the development of digital twin technology for Non-linear stochastic systems" and jointly organized by three laboratories of HSE University:
Programme
-
Nov 1
School09:30 - 10:00 Registration and welcome
10:00 - 11:15 Posterior sampling and Bayesian bootstrap. Part 1
11:15 - 11:45 Coffee break
11:45 - 13:00 Posterior sampling and Bayesian bootstrap. Part 2
13:00 - 14:00 Free time
14:00 - 15:15 Tensors and machine learning. Part 1
15:15 - 15:35 Сoffee break
15:35 - 16:50 Tensors and machine learning. Part 2
17:00 - 17: 30 Local-Global MCMC kernels: the best of both worlds
17:30 - 18:00 Computer vision on mobile devices
Nov 2
School10:00 - 11:15 Optimal Transport and Generative Modeling based on Stochastic Processes. Part 1
11:15 - 11:45 Coffee break
11:45 - 13:00 Optimal Transport and Generative Modeling based on Stochastic Processes. Part 2
13:00 - 14:00 Free time
14:00 - 15:15 Introduction to diffusion models. Part 1
15:15 - 15:35 Coffee break
15:35 - 16:50 Introduction to diffusion models. Part 2
17:00 - 17:30 Machine learning and astrophysics
17:30 - 18:00 Machine Learning Challenges in Particle Physics
Nov 3
Conference10:00 - 11:15 Session 1: Applied ML & Session 2: Optimization
11:15 - 11:45 Сoffee break
11:45 - 13:00 Session 3: Applied ML 2 & Session 4: Computational ML
13:00 - 14:00 Free time
14:00 - 15:15 Session 5: Theoretical ML & Session 6: Generative modeling and representation learing
15:15 - 15:45 Сoffee break
15:45 - 16:00 Conference Photo
16:00 - 16:05 MML Olympiad award ceremony
16:05 - 17:30 Poster session
17:30 - 19:30 Conference Dinner
Slides of talks
Alexey Naumov, Daniil Tiapkin - Part 1. Posterior sampling and Bayesian bootstrap: sample complexity and regret bounds
Alexey Naumov, Daniil Tiapkin - Part 2. Posterior Sampling and Bayesian Bootstrap in Reinforcement Learning
Ivan Oseledets - Part 1. Tensors and machine learning
Ivan Oseledets - Part 2. Tensors and machine learning
Sergey Samsonov - Local-Global MCMC kernels: the best of both worlds
Andrey Savchenko - Computer vision on mobile devices
Evgeny Burnaev - Part 1. Optimal Transport and Generative Modeling based on Stochastic Processes
Evgeny Burnaev - Part 2. Optimal Transport and Generative Modeling based on Stochastic Processes
Evgeny Burnaev - Part 3. Optimal Transport and Generative Modeling based on Stochastic Processes
Dmitry Vetrov, Dmitry Molchanov - Introduction to diffusion models
Ivan Kharuk - Machine learning and astrophysics
Denis Derkach - Machine Learning Challenges in Particle Physics
Video
Organisers
Polina Dergacheva
