Generative Modeling by Estimating Gradients of the Data Distribution - Stefano Ermon

Generative Modeling by Estimating Gradients of the Data Distribution - Stefano Ermon

Institute for Advanced Study via YouTube Direct link

Data Modes

12 of 16

12 of 16

Data Modes

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. 1 Intro
  2. 2 Progress in generative models of text
  3. 3 Implicit Generative Models Implicit models: directly represent the sampling process
  4. 4 Representation of Probability Distributions
  5. 5 Learning Deep Energy-Based Models using Scores
  6. 6 Learning with Sliced Score Matching
  7. 7 Experiments: Scalability and Speed
  8. 8 Experiments: Fitting Deep Kernel Exponential Families
  9. 9 From Score Estimation to Sample Generation
  10. 10 Pitfall 1: Manifold Hypothesis
  11. 11 Pitfall 2: Inaccurate Score Estimation in Low Data-Density Regions
  12. 12 Data Modes
  13. 13 Gaussian Perturbation
  14. 14 Annealed Langevin Dynamics
  15. 15 Joint Score Estimation
  16. 16 Experiments: Sampling

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.