Completed
Experiments: Fitting Deep Kernel Exponential Families
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Generative Modeling by Estimating Gradients of the Data Distribution - Stefano Ermon
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Progress in generative models of text
- 3 Implicit Generative Models Implicit models: directly represent the sampling process
- 4 Representation of Probability Distributions
- 5 Learning Deep Energy-Based Models using Scores
- 6 Learning with Sliced Score Matching
- 7 Experiments: Scalability and Speed
- 8 Experiments: Fitting Deep Kernel Exponential Families
- 9 From Score Estimation to Sample Generation
- 10 Pitfall 1: Manifold Hypothesis
- 11 Pitfall 2: Inaccurate Score Estimation in Low Data-Density Regions
- 12 Data Modes
- 13 Gaussian Perturbation
- 14 Annealed Langevin Dynamics
- 15 Joint Score Estimation
- 16 Experiments: Sampling
