CSC 665 Section 2: Machine Learning Theory - Fall 2019

Designed mainly as a more theoretically-oriented version of CSC 580 Principles of Machine Learning, students will learn, via the lens of mathematical foundations, how and when machine learning is possible/impossible as well as various algorithms with theoretical guarantees. Specifically, the course offers mathematical formulation of learning environments (e.g., stochastic and adversarial worlds with possibly limited feedback), fundamental limits of learning in these environments, various algorithms concerning sample efficiency, computational efficiency, and generality. Throughout, students will not only learn fundamental mathematical tools upholding the current understanding of machine learning systems in the research community but also develop skills of adapting these techniques to their own research needs such as developing new algorithms.

Logistics info

TuTh 12:30-1:45pm

Gould-Simpson 856

Piazza link access code: CSC665-2

Gradescope entry code: 95D244 (Note: for the calibration homework, please still submit a physical copy in class; we will be using gradescope from HW 1 onwards.)

Instructor

Chicheng Zhang

Gould-Simpson 720

chichengz@cs.arizona.edu

Office Hour: Mondays 1-2pm or by email appointment

Textbook

There is no designated textbook for this course. Much of the course materials will be based on the following books (in the order of appearance in class schedule):

Understanding machine learning: from theory to algorithms by Shai Shalev-Shwartz and Shai Ben-David (SSBD)

Introduction to online optimization by Elad Hazan (H)

Bandit algorithms by Tor Lattimore and Csaba Szepesvari (LS)

The following set of surveys and books also provide a good coverage of relevant materials:

Online learning and online convex optimization by Shai Shalev-Shwartz

Regret analysis of stochastic and nonstochastic multi-armed bandit problems by Sebastien Bubeck and Nicolo Cesa-Bianchi

Introduction to Multi-Armed Bandits by Alex Slivkins

Review for prerequisites

Here are some excellent notes for probability review and linear algebra review.

Machine learning courses at UA

CSC 535 Probabilistic Graphical Models by Kobus Barnard

[ISTA 457/INFO 557 Neural Networks] by Steven Bethard

CSC 665 Topics in Online Learning and Bandits by Kwang-Sung Jun (Spring 2020)

INFO 521 Introduction to Machine Learning by Clayton Morrison

CSC 665 Section 1 Advanced Topics in Probabilistic Graphical Models by Jason Pacheco (Fall 2019)

CSC 580 Principles of Machine Learning by Carlos Scheidegger

MIS 601 Statistical Foundations of Machine Learning by Junming Yin

MATH 574M Statistical Machine Learning by Helen Zhang

Learning theory courses at other institutions

The following is a far-from-complete list of learning theory courses offered at other institutions:

Foundations of Machine Learning and Data Science by Nina Balcan and Avrim Blum

Statistical Learning Theory by Peter Bartlett

Topics in Learning Theory by Daniel Hsu

Theoretical Machine Learning by Rob Schapire

Machine Learning Theory by Matus Telgarsky

Learning Theory by Sham Kakade and Ambuj Tewari