Embedding as a Tool for Algorithm Design

Embedding as a Tool for Algorithm Design

Simons Institute via YouTube Direct link

Intro

1 of 20

1 of 20

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Embedding as a Tool for Algorithm Design

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

  1. 1 Intro
  2. 2 Embedding algorithms
  3. 3 Prediction for structured data
  4. 4 Big dataset, explosive feature space
  5. 5 Combinatorial optimizations over graphs
  6. 6 Key observation & fundamental question
  7. 7 Represent structure as latent variable model (LVM)
  8. 8 Posterior distribution as features
  9. 9 Mean field algorithm aggregates information
  10. 10 What's embedding?
  11. 11 Learning via embedding
  12. 12 Embedding mean field
  13. 13 Directly parameterize nonlinear mapping
  14. 14 Embed belief propagation
  15. 15 New tools for algorithm design
  16. 16 Motivation 2: Dynamic processes over networks
  17. 17 Unroll: time-varying dependency structure
  18. 18 Embedding algorithm for building generative model
  19. 19 Scenario 3: Combinatorial optimization over graph
  20. 20 Greedy algorithm as Markov decision process

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.