My website has moved to https://raf.prof. If you are not redirected within 2 seconds, click here.
Online Machine Learning, Forecasting, and e-Values
When: TTh 2:00-3:15pm
Where: ECCR 1B51 and Zoom (only for CU Boulder; email me if you want to join outside of CU)
Professor: Rafael Frongillo
Syllabus: below; more details soon
Assignments, grades: Canvas
Schedule, papers, signups: spreadsheet coming soon
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
- Week 1-2: Online machine learning
- Week 3-4: Game-theoretic probability and e-values
- Week 5-13: Paper presentations, project updates
- Week 14-16: Project presentations