Completed
PERFORMANCE OF GRADIENT DESCENT
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Insights on Gradient-Based Algorithms in High-Dimensional Learning
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 WORKHORSE OF MACHINE LEARNIN
- 3 IN DEEP LEARNING
- 4 STRATEGY
- 5 WHY THIS MODEL?
- 6 ESTIMATORS
- 7 GRADIENT-BASED ALGORITHMS
- 8 DYNAMICAL MEAN FIELD THEORY
- 9 LANGEVIN STATE EVOLUTION (NUMERICAL SOLUTION)
- 10 LANGEVIN PHASE DIAGRAM
- 11 GRADIENT-FLOW PHASE DIAGRAM
- 12 POPULAR "EXPLANATION"
- 13 SPURIOUS MINIMA DO NOT NECESSARILY CAUSE GF TO FAIL
- 14 WHAT IS GOING ON?
- 15 TRANSITION RECIPE
- 16 TRANSITION CONJECTUR
- 17 LANDSCAPE ANALYSIS
- 18 CONCLUSION ON SPIKED MATRIX-TENSOR MODEL
- 19 TEACHER-NEURAL SETTING
- 20 TEACHER STUDENT PERCEPTRON
- 21 PHASE RETRIEVAL: OPTIMAL SOLUTION
- 22 GRADIENT DESCENT FOR PHASE RETRIEVAI
- 23 PERFORMANCE OF GRADIENT DESCENT
- 24 GRADIENT DESCENT NUMERICALLY
- 25 TOWARDS A THEORY
- 26 OVER-PARAMETRISED LANDSPACE
- 27 STOCHASTIC GRADIENT DESCENT
- 28 DYNAMICAL MEAN-FIELD THEOR Mignaco, Urbani, Krzakala, LZ, 2006.06098
- 29 DMFT FOLLOWS THE WHOLE TRAJECTORY
