Explores the trade-off between complexity and risk in machine learning models, the benefits of overparametrization, and the implicit bias of optimization algorithms.
Covers the general logistics, course rationale, prerequisites, organization, credits, workload, grading, and course content, including swarm intelligence, foraging strategies, and collective phenomena.
Covers optimization techniques in machine learning, focusing on convexity, algorithms, and their applications in ensuring efficient convergence to global minima.
