Online Machine Learning, Forecasting, and e-Values

When: TTh 2:00-3:15pm
Where: ECCS 1B14 and Zoom (password all lowercase: "ville") Professor: Rafael Frongillo
Syllabus: below
Assignments, grades: Canvas
Communication: Zulip
Schedule, papers, signups: Spreadsheet


Syllabus

Overview

This class will explore various topics in online machine learning, forecasting, and e-values, a newly proposed robust alternative to the ubiquitous p-value in science and engineering. A theme underpinning the course is that for many algorithms or statistical tests, performance guarantees under probabilistic uncertainty about the world continue to hold even when the world is adversarial (worst-case, in some sense). We will study when and how to extend such guarantees to the worst-case, in a variety of contexts, using tools from game-theoretic probability and the minimax theorem.

The class will begin with lectures to give adequate background, and then transition to student presentations on related research papers. Assessment will be based on participation in discussions, a final project on a topic related to the course, and occasional light problem sets on foundational concepts. Students with backgrounds outside of computer science are welcome. Students who are primarily interested in only a subset of the topics are still encouraged to enroll.

Prerequisites: I would suggest a solid background in algorithms, and "mathematical maturity" (meaning a grasp of proof writing and balancing intuition with formal arguments).

Tentative Schedule

Guidelines for paper presentations

When you present a paper to the class, you should prepare slides that go over the paper in detail, aiming for about 30 minutes. Here is a rough guideline that you should feel free to deviate from:

You should email me your slides at least 3 days before your presentation so that I can give you feedback. (Even better to email me an outline of your slides 4+ days before, so you don't spend time on slides that I'll suggest cutting / you won't have time for!)

Final Project

For your final project, you are welcome to work alone or in groups of 2 (maybe 3 if we have enough students). The purpose of the project is to engage in research related to the topics covered in class. This could mean exploring a connection with your existing research, tackling one of the open problems discussed in class, or coming up with your own topic or question (related to class of course). The final product of the project will be a report written in the style of a scientific paper which describes the findings (see below). For students preferring a more "expository" project, where they focus on understanding existing research / material rather than trying to extend it, let me know and we can probably come up with some suitable ideas.

The following components comprise your final project grade:

Resources

Information elicitation tutorial

LaTeX resources and guides: one, two, three, four