Random Initialization and Implicit Regularization in Nonconvex Statistical Estimation - Lecture 2

Random Initialization and Implicit Regularization in Nonconvex Statistical Estimation - Lecture 2

Georgia Tech Research via YouTube Direct link

Intro

1 of 16

1 of 16

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Random Initialization and Implicit Regularization in Nonconvex Statistical Estimation - Lecture 2

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

  1. 1 Intro
  2. 2 Statistical models come to rescue
  3. 3 Example: low-rank matrix recovery
  4. 4 Solving quadratic systems of equations
  5. 5 A natural least squares formulation
  6. 6 Rationale of two-stage approach
  7. 7 What does prior theory say?
  8. 8 Exponential growth of signal strength in Stage 1
  9. 9 Our theory: noiseless case
  10. 10 Population-level state evolution
  11. 11 Back to finite-sample analysis
  12. 12 Gradient descent theory revisited
  13. 13 A second look at gradient descent theory
  14. 14 Key proof idea: leave-one-out analysis
  15. 15 Key proof ingredient: random-sign sequences
  16. 16 Automatic saddle avoidance

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.