Gradient Descent on Infinitely Wide Neural Networks - Global Convergence and

Gradient Descent on Infinitely Wide Neural Networks - Global Convergence and

International Mathematical Union via YouTube Direct link

Intro

1 of 18

1 of 18

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Gradient Descent on Infinitely Wide Neural Networks - Global Convergence and

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Machine learning Scientific context
  3. 3 Parametric supervised machine learning
  4. 4 Convex optimization problems
  5. 5 Theoretical analysis of deep learning
  6. 6 Optimization for multi-layer neural networks
  7. 7 Gradient descent for a single hidden layer
  8. 8 Wasserstein gradient flow
  9. 9 Many particle limit and global convergence (Chizat and Bach, 2018)
  10. 10 From optimization to statistics
  11. 11 Interpolation regime
  12. 12 Logistic regression for two-layer neural networks
  13. 13 From RKHS norm to variation norm
  14. 14 Kernel regime
  15. 15 Optimizing over two layers
  16. 16 Comparison of kernel and feature learning regimes
  17. 17 Discussion
  18. 18 Conclusion

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.