1:04:32

[DeepBayes2019]: Day 3, Lecture 3. Normalizing flows

38:40

[DeepBayes2019]: Day 3, Practical session 2. Generative adversarial networks

1:18:09

[DeepBayes2019]: Day 3, Lecture 1. Generative adversarial networks

1:23:50

[DeepBayes2019]: Day 2, Keynote Lecture 5. Fair machine learning

21:25

[DeepBayes2019]: Day 2, practical session 4. Discrete variable models

59:18

[DeepBayes2019]: Day 2, Lecture 3. Discrete variable models

38:34

[DeepBayes2019]: Day 2, practical session 2. Variational autoencoders

1:16:30

[DeepBayes2019]: Day 2, Lecture 1. Stochastic variational inference and variational autoencoders

36:25

[DeepBayes2019]: Day 1, practical session 5. Approximate Bayesian inference

1:02:55

[DeepBayes2019]: Day 1, Lecture 3. Variational inference

1:02:32

[DeepBayes2019]: Day 1, Lecture 4. Latent variable models and EM-algorithm

1:14:36

Variational Inference for Reinforcement Learning in Partially Observable Markov Decision Processes

1:21:26

The Kanerva Machine

1:27:31

[In Russian] Спиновые стёкла - основы теории

1:40:10

[In Russian] Introduction to Riemannian Optimization and Its Application on Matrix Manifolds

36:58

Sparse Bayesian Variational Learning with Matrix Normal Distributions

1:35:35

Importance Weighted Hierarchical Variational Inference

1:06:53

Continuous Normalizing Flows

2:11:54

Лекция про Первую Мировую войну. Дмитрий Ветров, Екатерина Волженина. 9 ноября 2018 г.

45:31

Neural Ordinary Differential Equations

1:13:56

SWAG: Approximate Bayesian Inference Using SGD Trajectory

39:33

Scaling Matters in Deep Structured-Prediction Models

52:03

Pairwise Augmented GANs with Adversarial Reconstruction Loss

50:01

Maximum Entropy, Spectra of Graphs, Understanding the loss surface of DNN’s with Spectral Techniques

1:34:22

Predicting Oil Movement in a Development System using Deep Latent Dynamics Models

1:09:43

Hamiltonian Monte-Carlo for Orthogonal Matrices

1:29:16

Quantifying Learning Guarantees for Convex but Inconsistent Surrogates

1:11:29

(Doubly) Semi-Implicit Variational Inference

1:09:31

Deep Weight Prior

44:45

Optimization of Proposal Distribution for the Metropolis-Hastings Algorithm

1:24:26

Deep Learning for Drug Discovery

1:45:33

Variational Sequential Monte Carlo

1:15:46

Variational Inference with Implicit Distributions

1:18:28

[DeepBayes2018]: Day 6, Invited talk 4. Information bottleneck

1:02:03

[DeepBayes2018]: Day 2, lecture 2. Scalable Bayesian methods

1:32:20

[DeepBayes2018]: Day 2, lecture 1. Introduction to stochastic optimization

7:32

[DeepBayes2018]: Day 1, practical session 5. EM-algorithm (part 2)

43:32

[DeepBayes2018]: Day 1, practical session 4. EM-algorithm (part 1)

1:31:59

[DeepBayes2018]: Day 1, lecture 3. Models with latent variables and EM-algorithm

28:11

[DeepBayes2018]: Day 1, practical session 2. Bayesian reasoning

10:22

[DeepBayes2018]: Day 6, Practical session 3. Neural networks sparsification

1:08:39

[DeepBayes2018]: Day 6, Lecture 2. Sparse variational dropout and variance networks

1:21:06

[DeepBayes2018]: Day 6, Lecture 1. Bayesian neural networks and variational dropout

1:08:29

[DeepBayes2018]: Day 5, Lecture 5. Stochastic Markov chain Monte Carlo

56:20

[DeepBayes2018]: Day 5, lecture 4. Markov chain Monte Carlo

1:35:43

[DeepBayes2018]: Day 5, Invited talk 3. Deep Gaussian processes

1:22:19

[DeepBayes2018]: Day 5, Practical session 2. Bayesian optimization

1:28:01

[DeepBayes2018]: Day 5, Lecture 1. Gaussian processes

31:35

[DeepBayes2018]: Day 4, Sponsor talk 4. Yaroslav LabutinRymsho. Samsung Research

1:25:08

[DeepBayes2018]: Day 4, Invited talk 3. Extending the Reparameterization Trick

12:44

[DeepBayes2018]: Day 4, Practical session 2. Adversarial learning

1:13:14

[DeepBayes2018]: Day 4, lecture 1. Generative models

27:38

[DeepBayes2018]: Day 3, Practical session 5. Distributional reinforcement learning

1:02:19

[DeepBayes2018]: Day 3, lecture 4. Distributional reinforcement learning

59:27

[DeepBayes2018]: Day 3, Practical session 3. Reinforcement learning

1:05:49

[DeepBayes2018]: Day 3, IT 2. Reinforcement learning through the lense of variational inference

1:41:54

[DeepBayes2018]: Day 3, Invited talk 1. Advanced methods of variational inference

21:51

[DeepBayes2018]: Day 2, practical session 5. Variational autoencoders

1:15:51

[DeepBayes2018]: Day 2, lecture 4. Discrete latent variables

1:31:32

[DeepBayes2018]: Day 2, lecture 3. Variational autoencoders

1:13:04

Variance Networks, Dmitry Molchanov

1:12:09

Universal Conditional Machine, Oleg Ivanov

1:24:46

New critical and collective phenomena in random networks and graphs, Alexander Gorsky

1:47:47

Learning in Partially Observable Markov Decision Processes, Pavel Shvechikov

1:08:23

Hierarchical methods for Reinforcement Learning, Evgenii Nikishin

1:06:00

Loss Surfaces, fast ensembling and weight averaging of DNNs, Timur Garipov

1:33:57

Deep Bayesian regression models, Aliaksandr Hubin

1:05:33

Stochastic Batch Normalization, Andrey Atanov

1:37:55

Stochastic computational graphs: optimization and applications in NLP, Maksim Kretov

1:20:06

Bayesian Methods in Generative Adversarial Networks, Alexey Umnov

4:21

Structured Bayesian Pruning (NIPS 2017 Spotlight video)

1:19:02

Stochastic Computation Graphs, Part 2, Artem Sobolev

1:46:20

Stochastic Computation Graphs, Part 1, Artem Sobolev

1:22:59

Tensor Train Decomposition for Fast Learning in Large Scale Gaussian Process Models, Dmitry Kropotov

1:35:59

Mini-Workshop: Stochastic Processes and Probabilistic Models in Machine Learning. Day 2. Part 2.

1:41:15

Mini-Workshop: Stochastic Processes and Probabilistic Models in Machine Learning. Day 2. Part 1.

51:25

Structured Bayesian Pruning via Log-Normal Multiplicative Noise, Kirill Nekludov

1:25:37

AdaGAN: Boosting Generative Models, Iliya Tolstikhin

1:28:15

On Structured Prediction Theory with Calibrated Convex Surrogate Losses, Anton Osokin