Computer Science 690M - Machine Learning Theory

When, how, and why do machine learning algorithms work? This course answers these ques- tions by studying the theoretical aspects of machine learning, with a focus on statistically and computationally efficient learning. Broad topics will include: PAC-learning, uniform convergence, and model selection; supervised learning algorithms including SVM, boosting, kernel methods; online learning algorithms and analysis; unsupervised learning with guarantees. Special topics may include: Bandits, active learning, semi-supervised learning and others.

Open to COMPSCI graduate students only. Pre Req: COMPSCI 689 INSTRUCTOR PERMISSION REQUIRED FOR UNDERGRADUATE CS MAJORS CLEARED BY THE UPD, IF AVAILABLE SEATS. STUDENTS WITH COMPSCI 589 MAY BE CONSIDERED WITH INSTRUCTOR PERMISSION. SEATS SAVED FOR INCOMING STUDENT REGISTRATION. STUDENTS NEEDING SPECIAL PERMISSION MUST REQUEST OVERRIDES VIA THE ON-LINE FORM: https://www.cics.umass.edu/overrides.