HSE-Yandex autumn school on generative models
from
Tuesday 26 November 2019 (09:00)
to
Friday 29 November 2019 (19:00)
Monday 25 November 2019
Tuesday 26 November 2019
09:45
Welcome
Welcome
09:45 - 10:00
Room: room "Oxford"
10:00
Simple generative models. Generative adversarial networks 1
Simple generative models. Generative adversarial networks 1
10:00 - 11:00
Room: room "Oxford"
11:00
Coffee Break
Coffee Break
11:00 - 11:30
Room: room "Oxford"
11:30
Simple generative models. Generative adversarial networks 2
Simple generative models. Generative adversarial networks 2
11:30 - 12:30
Room: room "Oxford"
12:30
Lunch
Lunch
12:30 - 14:00
14:00
Optimization methods for optimal transport 1
Optimization methods for optimal transport 1
14:00 - 15:00
Room: room "Oxford"
15:00
Tea Break
Tea Break
15:00 - 15:30
Room: room "Oxford"
15:30
Optimization methods for optimal transport 2
Optimization methods for optimal transport 2
15:30 - 16:30
Room: room "Oxford"
16:30
New directions in generative models and high-dimensional MC methods
New directions in generative models and high-dimensional MC methods
16:30 - 17:30
Room: room "Oxford"
Wednesday 27 November 2019
10:00
Computational and statistical optimal transport 3
Computational and statistical optimal transport 3
10:00 - 11:00
Room: room "Oxford"
11:00
Coffee Break
Coffee Break
11:00 - 11:30
Room: room "Oxford"
11:30
Computational and statistical optimal transport 4
Computational and statistical optimal transport 4
11:30 - 12:30
Room: room "Oxford"
12:30
Group Photo 1
Group Photo 1
12:30 - 12:40
Room: room "Oxford"
12:40
Lunch
Lunch
12:40 - 14:00
14:00
Introduction to scalable Bayesian methods 1
Introduction to scalable Bayesian methods 1
14:00 - 15:00
Room: room "Oxford"
15:00
Tea Break
Tea Break
15:00 - 15:30
Room: room "Oxford"
15:30
Introduction to scalable Bayesian methods 2
Introduction to scalable Bayesian methods 2
15:30 - 16:30
Room: room "Oxford"
Thursday 28 November 2019
10:00
Advanced generative models. Introduction to normalizing flows 1
Advanced generative models. Introduction to normalizing flows 1
10:00 - 11:00
Room: room "Oxford"
11:00
Coffee Break
Coffee Break
11:00 - 11:30
Room: room "Oxford"
11:30
Advanced generative models. Introduction to normalizing flows 2
Advanced generative models. Introduction to normalizing flows 2
11:30 - 12:30
Room: room "Oxford"
12:30
Lunch
Lunch
12:30 - 14:00
Room: room "Oxford"
14:00
RPGAN: random paths as a latent space for GAN interpretability
RPGAN: random paths as a latent space for GAN interpretability
14:00 - 14:30
Room: room "Oxford"
14:30
Sequence modeling with unconstrained generation order
Sequence modeling with unconstrained generation order
14:30 - 15:00
Room: room "Oxford"
15:00
Tea Break
Tea Break
15:00 - 15:30
Room: room "Oxford"
15:30
Introduction to scalable Bayesian methods 3
Introduction to scalable Bayesian methods 3
15:30 - 16:30
Room: room "Oxford"
16:30
Introduction to scalable Bayesian methods 4
Introduction to scalable Bayesian methods 4
16:30 - 17:30
Room: room "Oxford"
19:00
Conference dinner (В лофте Studiohall. Адрес: Ленинский пр. Д. 49)
Conference dinner (В лофте Studiohall. Адрес: Ленинский пр. Д. 49)
19:00 - 21:00
Room: TBA
Friday 29 November 2019
10:00
Bayesian inference vs stochastic optimization
Bayesian inference vs stochastic optimization
10:00 - 10:50
Room: Mouline Rouge
10:50
Wasserstein-2 Generative Networks
Wasserstein-2 Generative Networks
10:50 - 11:30
Room: Mouline Rouge
11:30
Group Photo 2
Group Photo 2
11:30 - 11:40
Room: room "Oxford"
11:40
Coffee Break
Coffee Break
11:40 - 12:10
Room: Mouline Rouge
12:10
Towards Photorealistic Neural Avatars
Towards Photorealistic Neural Avatars
12:10 - 12:50
Room: Mouline Rouge
12:50
Adaptive Divergence for Rapid Adversarial Optimization
Adaptive Divergence for Rapid Adversarial Optimization
12:50 - 13:10
Room: Mouline Rouge
13:10
(1+ε)-class Classification: an Anomaly Detection Method for Highly Imbalanced or Incomplete Data Sets
(1+ε)-class Classification: an Anomaly Detection Method for Highly Imbalanced or Incomplete Data Sets
13:10 - 13:30
Room: Mouline Rouge
13:30
Lunch
Lunch
13:30 - 14:40
14:40
Approximation of multivariate functions using deep learning with applications
Approximation of multivariate functions using deep learning with applications
14:40 - 15:20
Room: Mouline Rouge
15:20
Structure-adaptive manifold estimation
Structure-adaptive manifold estimation
15:20 - 15:50
Room: Mouline Rouge
15:50
Tea Break
Tea Break
15:50 - 16:20
Room: Mouline Rouge
16:20
Uncertainty estimation: can your neural network provide confidence for its predictions?
Uncertainty estimation: can your neural network provide confidence for its predictions?
16:20 - 16:50
Room: Mouline Rouge
16:50
Fast Simulation Using Generative Adversarial Networks in LHCb
Fast Simulation Using Generative Adversarial Networks in LHCb
16:50 - 17:15
Room: Mouline Rouge
17:15
Differentiating the Black-Box: Optimization with Local Generative Surrogates
Differentiating the Black-Box: Optimization with Local Generative Surrogates
17:15 - 17:40
Room: Mouline Rouge
17:40
The end
The end
17:40 - 17:50
Room: Mouline Rouge