Learning From Ranks, Learning to Rank - Jean-Philippe Vert, Google Brain

Learning From Ranks, Learning to Rank - Jean-Philippe Vert, Google Brain

Alan Turing Institute via YouTube Direct link

Goals

6 of 24

6 of 24

Goals

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Learning From Ranks, Learning to Rank - Jean-Philippe Vert, Google Brain

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

  1. 1 Intro
  2. 2 Differentiable programming
  3. 3 Beyond images and strings
  4. 4 What if inputs or outputs are permutations?
  5. 5 Examples
  6. 6 Goals
  7. 7 Permutations as inputs
  8. 8 SUQUAN embedding (Le Morvan and Vert, 2017)
  9. 9 Supervised ON (SUQUAN)
  10. 10 Experiments: CIFAR-10
  11. 11 Limits of the SUQUAN embedding
  12. 12 The Kendall embedding (Jiao and Vert, 2015, 2017)
  13. 13 Geometry of the embedding
  14. 14 Kendall and Mallows kernels
  15. 15 Applications
  16. 16 Remark
  17. 17 Permutations as intermediate / output?
  18. 18 Optimal transport (OT)
  19. 19 Differentiable permutation matrix
  20. 20 Differentiable sort and rank
  21. 21 Soft quantization and soft quantiles
  22. 22 Application: soft top-k loss
  23. 23 Application: learning to sort
  24. 24 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.