Algorithmic Thresholds for Spherical Spin Glasses in High-Dimensional Optimization

Algorithmic Thresholds for Spherical Spin Glasses in High-Dimensional Optimization

Harvard CMSA via YouTube Direct link

Introduction

1 of 42

1 of 42

Introduction

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Algorithmic Thresholds for Spherical Spin Glasses in High-Dimensional Optimization

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

  1. 1 Introduction
  2. 2 Outline
  3. 3 Motivation
  4. 4 Problem Statement
  5. 5 tensor PCA
  6. 6 maximum likelihood estimator
  7. 7 Random cubic polynomial
  8. 8 Larger degree polynomial
  9. 9 Where does it come from
  10. 10 Random graph example
  11. 11 Random models
  12. 12 Efficient optimization
  13. 13 Brute Force search
  14. 14 Easing models
  15. 15 Random case set
  16. 16 Optimization
  17. 17 Optimization Algorithm
  18. 18 Subog
  19. 19 Moving Radially
  20. 20 Other Questions
  21. 21 General Models
  22. 22 Overlap Gap Property
  23. 23 Example
  24. 24 Stable Algorithms
  25. 25 Overlap Gap
  26. 26 Random KSAT
  27. 27 Algorithm Stability
  28. 28 Overlap Concentration
  29. 29 Additional Results
  30. 30 combinatorial optimization
  31. 31 matching random graphs
  32. 32 multispecies spin glass
  33. 33 Hamiltonian bias
  34. 34 Linear term bias
  35. 35 Complex energy functions
  36. 36 Binary perceptron model
  37. 37 Neural network memorization
  38. 38 Isolated solutions
  39. 39 Dense clusters of solutions
  40. 40 Lunge event dynamics
  41. 41 Mixed models
  42. 42 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.