How Much Data Is Sufficient to Learn High-Performing Algorithms?

How Much Data Is Sufficient to Learn High-Performing Algorithms?

Institute for Pure & Applied Mathematics (IPAM) via YouTube Direct link

Intro

1 of 17

1 of 17

Intro

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

How Much Data Is Sufficient to Learn High-Performing Algorithms?

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

  1. 1 Intro
  2. 2 Data-driven algorithm design
  3. 3 Sequence alignment algorithms
  4. 4 Automated configuration
  5. 5 This talk: Main result
  6. 6 Domains with piecewise structure
  7. 7 Primary challenge in combinatorial domains
  8. 8 Example: Sequence alignment
  9. 9 Algorithmic performance
  10. 10 Generalization bounds
  11. 11 Piecewise constant utility function
  12. 12 Primal & dual classes
  13. 13 Warmup: 1-dimensional parameters
  14. 14 Intrinsic complexity
  15. 15 Main result (informal)
  16. 16 Outline
  17. 17 Piecewise constant dual functions

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.