From Classical Statistics to Modern Machine Learning

From Classical Statistics to Modern Machine Learning

Simons Institute via YouTube Direct link

"Double descent" risk curve

12 of 23

12 of 23

"Double descent" risk curve

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

From Classical Statistics to Modern Machine Learning

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

  1. 1 Intro
  2. 2 Supervised ML
  3. 3 Generalization bounds
  4. 4 Classical U-shaped generalization curve
  5. 5 Does interpolation overfit?
  6. 6 Interpolation does not overfit even for very noisy data
  7. 7 Deep learning practice
  8. 8 Generalization theory for interpolation?
  9. 9 A way forward?
  10. 10 Interpolated k-NN schemes
  11. 11 Interpolation and adversarial examples
  12. 12 "Double descent" risk curve
  13. 13 what is the mechanism?
  14. 14 Double Descent in Linear regression
  15. 15 Occams's razor
  16. 16 The landscape of generalization
  17. 17 where is the interpolation threshold?
  18. 18 Optimization under interpolation
  19. 19 SGD under interpolation
  20. 20 The power of interpolation
  21. 21 Learning from deep learning: fast and effective kernel machines
  22. 22 Important points
  23. 23 From classical statistics to modern ML

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.