ePOWERAI
CoursesAdv. Optimization

Optimization

Advanced Optimization

Boyd-depth duality and cone programs meet second-order, distributed, and sharpness-aware training — the bridge from convex structure to modern large-scale ML optimization.

5 modules · 14 lessons · runs in your browser · no account

Your progress00 / 14 · 0%

Course contents

Duality & KKT

  1. W01Week 1: Optimality Conditions Revisited
  2. W02Week 2: Lagrangian Duality in Depth
  3. W03Week 3: KKT and Sensitivity

Cones & IPMs

  1. W04Week 4: LP, QP, and Conic Form
  2. W05Week 5: Semidefinite Programming
  3. W06Week 6: Interior-Point Methods
  4. W07Week 7: Proximal Methods and ADMM

Second-order & scale

  1. W08Week 8: Newton and Quasi-Newton
  2. W09Week 9: Variance Reduction
  3. W10Week 10: Large-Batch and Distributed Training

Geometry & training science

  1. W11Week 11: Automatic Differentiation
  2. W12Week 12: Sharpness and SAM
  3. W13Week 13: Landscapes and Implicit Bias

Capstone

  1. W14Week 14: Capstone — Structure Meets Scale