10-813 Advanced Topics in Machine Learning Theory

12 units, Carnegie Mellon University

This course on the design and theoretical analysis of machine learning methods will cover important problems studied in modern theoretical machine learning. We will examine questions such as What guarantees can we prove on the performance of learning algorithms and What can we say about the inherent ease or difficulty of learning problems. We will examine these both in classic settings, and in more modern settings where we are learning, for example, more complex objects beyond simple classifiers such as algorithms, or in the context of multiagents learning systems. In addressing these and related questions we will make connections to statistics, algorithms, linear algebra, complexity theory, information theory, optimization, game theory, and empirical machine learning research.

Prerequisites: none listed

Courseweave needs JavaScript to show sections, workloads and planning tools.