David Duvenaud: Self-tuning Gradient Estimators for Discrete Random Variables

preview_player
Показать описание
"Self-tuning Gradient Estimators for Discrete Random Variables"

Invited talk at Symposium on Advances in Approximate Bayesian Inference, December 2, 2018 in Montreal.
  1. James McInerney
Рекомендации по теме
David Duvenaud: Self-tuning 0:35:36

David Duvenaud: Self-tuning Gradient Estimators for Discrete Random Variables

Yingzhen Li: Gradient 0:28:23

Yingzhen Li: Gradient Estimators for Implicit Models

CAIDA Talk - 0:58:49

CAIDA Talk - Dec 6, 2019 - David Duvenaud

Self-Tuning Networks: Amortizing 1:00:50

Self-Tuning Networks: Amortizing the Hypergradient Computation for Hyperparameter Optimization

David Duvenaud - 0:51:39

David Duvenaud - Latent Stochastic Differential Equations: An Unexplored Model Class

Latent Stochastic Differential 1:05:28

Latent Stochastic Differential Equations for Irregularly-Sampled Time Series - David Duvenaud

Composing Graphical Models 0:37:32

Composing Graphical Models With Neural Networks, w/ David Duvenaud - #96

David Duvenaud: When 1:02:46

David Duvenaud: When should we make our models continuous in time?

Research Sit Downs: 0:16:49

Research Sit Downs: Phil Blunsom and David Duvenaud

David Duvenaud | 1:19:44

David Duvenaud | Explaining decisions by generating counterfactuals

Generator-aware Discriminators & 0:25:35

Generator-aware Discriminators & Discriminator-aware Generators - David Duvenaud

RL Chapter 9 0:41:47

RL Chapter 9 Part2 (Semi-gradient estimation methods under value function approximation)

Implicit Reparameterization Gradients 1:04:26

Implicit Reparameterization Gradients -Andriy Mnih, DeepMind

E2: University of 0:37:29

E2: University of Toronto's David Duvenaud on the Future of AI & Academia

David Duvenaud | 0:21:02

David Duvenaud | Reflecting on Neural ODEs | NeurIPS 2019

Amortized Bayesian Optimization 0:07:40

Amortized Bayesian Optimization over Discrete Spaces

Your Brain on 0:45:02

Your Brain on Energy-Based Models: Applying and Scaling EBMs to Problems...- Will Grathwohl

Noisy natural gradient 0:38:49

Noisy natural gradient as variational inference - Roger Grosse

NeurIPS 2020 Tutorial: 1:51:35

NeurIPS 2020 Tutorial: Deep Implicit Layers

Evaluating Lossy Compression 1:01:37

Evaluating Lossy Compression Rates of Deep Generative Models - Roger Grosse

Directions in ML: 1:00:35

Directions in ML: Latent Stochastic Differential Equations: An Unexplored Model Class

On the Effectiveness 0:23:59

On the Effectiveness of Hybrid Mutual Information Estimation - ArXiv:2306.00608

[FFJORD] Free-form Continuous 0:25:15

[FFJORD] Free-form Continuous Dynamics for Scalable Reversible Generative Models (Part 1) | AISC

Continuous-time deconvolutional regression: 1:14:21

Continuous-time deconvolutional regression: A method for studying continuous dynamics in naturali...