ECE284 - Theoretical Machine Learning

Instructor(s): Pedarsani


This course studies the mathematical foundations of machine learning, and focuses on understanding the tradeoffs between statistical accuracy, scalability, and computation efficiency of machine learning and optimization algorithms. Topics include empirical risk minimization, convexity in learning, convergence analysis of gradient descent algorithm in both convex and non-convex settings, stochastic gradient descent, accelerated methods, fundamentals of neural networks, and reinforcement learning.