Description

COMS 6998-4 in Fall 2017 is an advanced graduate-level course on topics in learning theory. This semester, the course will focus on interactive learning and related topics.

Interactive learning concerns the process by which two or more agents (e.g., a human and a computer) work together to accomplish a learning task (e.g., construct an accurate classifier for news articles). By contrast, the basic model of “supervised machine learning” involves little or no interaction between the two agents. In this course, we will study the research literature on theoretical aspects of interactive learning models and some related topics (e.g., “interpretable models”).

One major omission in this course on interactive learning is reinforcement learning. Fortunately, there are two other courses this semester being offered that cover reinforcement learning in detail.

Prerequisites

You must have a solid background in multivariate calculus, linear algebra, basic probability, and algorithms. You must have general mathematical maturity and be comfortable with mathematical writing (e.g., mathematical arguments, derivations, and proofs). This is a theory course, so you will be expected to understand and produce mathematical arguments and proofs. Background in computational learning theory or equivalent is recommended; background in machine learning is neither necessary nor sufficient.

Readings

Readings will be assigned from notes, books, and research papers available on the web.

Course requirements

More details are available on the instructions page.

Lateness

No late assignment will be accepted except in the case of a valid medical or family emergency. If you have such an emergency, please present any confirmatory documentation (e.g., from a physician) to your academic adviser, and then have your adviser e-mail me about the circumstance.

Disability services

If you require accommodations or support services from Disability Services, comply with their policies and make any necessary arrangements within the first two weeks of the semester.

Academic rules of conduct

You are expected to adhere to the Academic Honesty policy of the Computer Science Department, as well as the following course-specific policies.

Collaboration

You are welcome and encouraged to discuss course materials and reading assignments with other students.

For each homework assignment, you may discuss the problems with up to two other students (i.e., a group of at most three students). You must list all discussants in your homework write-up. Discussion must not go as far as one person telling others how to solve a problem. You must write up your own solutions by yourself. You may not look at another student’s homework write-up (whether partial or complete).

Use of outside references

Outside reference materials and sources (i.e., texts and sources beyond the assigned reading materials for the course) may be used on homework assignments only if explicitly permitted by the instructor. Such references must be appropriately acknowledged in the homework write-up. You must always write up your solutions in your own words.

  • Sources obtained by searching the internet for answers or hints on assignments are never permitted.
  • Texts and sources on course prerequisites are permitted to use. If you need to look up a result in such a source, you should give a citation.
  • If you inadvertently come across the solution to a homework problem, you should acknowledge this source in your homework write-up (and the circumstance), but still do your best to produce a solution without looking at the source. You must, of course, write your solution in your own words.

Violations

Violation of any portion of these policies will result in a penalty to be assessed at the instructor’s discretion. This may include receiving a zero grade for the assignment in question AND a failing grade for the whole course, even for the first infraction.