COMP 150-CLT Computational Learning Theory

In this semester the course will focus on Computational Learning Theory. Machine learning algorithms can be used analyze available data and develop generalizations that are useful for handling future data or experience. Computational Learning Theory studies the computational complexity, data complexity, and convergence properties (bounds on error rates) of machine learning algorithms. The emphasis is on algorithms that are both efficient and have good convergence properties. Alternatively, for some machine learning problems we seek lower bounds on the amount of resources for any potential algorithm. Models vary from adversarial worst case scenarios to statistical settings where a random process generates the data. The course reviews classical results in this field and samples from recent developments.