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