IIT Bombay · Computer Science

Distributed Optimization and Machine Learning

Prof. Mayank Baranwal · 2025 · 47 free video lectures

Centralized access to information and its subsequent processing is often computationally prohibitive over large networks due to communication overhead and the scale of the problem. Consequently, such systems rely on control and optimization algorithms that are fully distributed or even…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. Lecture 1: Introduction to optimization
  2. Lecture 2: Analyzing optimization algorithms in continuous time domain
  3. Lecture 3: Course Outline
  4. Lecture 4: Basics of optimization problems
  5. Lecture 5: Convex sets and Convex functions
  6. Lecture 6: Strictly and strongly convex functions
  7. Lecture 7: Implications of strong convexity
  8. Lecture 8: Primal and dual optimization problems
  9. Lecture 9: Slaters condition
  10. Lecture 10: Analysis of gradient descent algorithm
  11. Lecture 11: KKT conditions
  12. Lecture 12: Acceleration under strong convexity
  13. Lecture 13: Accelerate the convergence even further
  14. Lecture 14: Stability theory
  15. Lecture 15: Connections to optimization problems
  16. Lecture 16: Exponential stability
  17. Lecture 17: Bregman Divergance
  18. Lecture 18: Rescaled Gradient Flow
  19. Lecture 19: Advanced Results on PL inequality: Part 1
  20. Lecture 20: Advanced Results on PL inequality: Part 2
  21. Lecture 21: Constrained Optimization Problem
  22. Lecture 22: Augmented Lagrangian
  23. Lecture 23: Method of Multipliers
  24. Lecture 24: Dual Ascent and Dual Decomposition
  25. Lecture 25: ADMM Algorithm
  26. Lecture 26: Basics of Graph Theory
  27. Lecture 27: Basics of Graph Theory-2
  28. Lecture 28: Consensus and Average Consensus
  29. Lecture 29: Consensus and Average Consensus-2
  30. Lecture 30: Consensus Algorithms
  31. Lecture 31: Consensus Algorithms-Fixed time
  32. Lecture 32: Distributed Economic Dispatch Problem
  33. Lecture 33: Algorithm for Uncapacitated EDP
  34. Lecture 34: Capacitated EDP
  35. Lecture 35: Algorithms for Distributed Optimization
  36. Lecture 36: Algorithms for Distributed Optimization-2
  37. Lecture 37: Continuous-time Distributed Optimization Algorithms
  38. Lecture 38: Introduction to Neural Networks
  39. Lecture 39: Large Scale Machine Learning
  40. Lecture 40: Decentralized Stochastic Gradient Descent
  41. Lecture 41: Decentralized Stochastic Gradient Descent -2
  42. Lecture 42: Introduction to Federated Learning
  43. Lecture 43: FedAvg Algorithm
  44. Lecture 44: Convergence Analysis of FL
  45. Lecture 45: Sources of Computational Heterogenity in FL
  46. Lecture 46: Objective Inconsistency Problem
  47. Lecture 47: General Update Rule

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IIT Bombay.

Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights