diochnos/teaching/CS5970/2020F
CS 5970 – Computational Learning Theory (Fall 2020)
Table of Contents
Course Description
Topics of machine learning theory. Learning using membership queries, equivalence queries, version spaces, decision trees, perceptrons. Probably approximately correct (PAC) learning, Occam algorithms, VC-dimension, sample sizes for distribution-independent learning. Representation issues, proper learning, reductions, intractability, learning in the realizable case, agnostic learning. Noise models, statistical queries, PAC learning under noise. Adversarially robust learning against poisoning attacks and against adversarial examples. Distribution-specific learning and evolvability. Online learning and learning with expert advice in the mistake bound model. Weak and strong learning (boosting).
[Course Description] [Table of Contents] [Top]
Basic Information
Syllabus
The syllabus is available here.
Time and Location
Mondays, Wednesdays, and Fridays, 9:30am – 10:20am, Devon Energy Hall 0120.
Contact Information
Please see here.
Office Hours
I will be holding my office hours at the following times.
- Mondays
- 10:30am – 12:30pm, 244 Devon Energy Hall
- Wednesdays
- 10:30am – 12:30pm, 244 Devon Energy Hall
Please note that while anyone is welcome during the entire 2-hour time period on Mondays and Wednesdays, CS 5970 will have precedence during the first hour (10:30am – 11:30am) and CS 4033/5033 will have precedence during the second hour (11:30am – 12:30pm).
Exceptions to the Regular Schedule of Office Hours
If you want to meet me outside of my office hours, please send me an email and arrange an appointment.
[Basic Information] [Table of Contents] [Top]
Important Coronavirus-Related Information
We have the following links.
- Additional Technologies
- Questions and Answers about the Coronavirus
- Instructional Faculty
- Masking Policy Syllabus Statement — Also has a link to a webpage with full details.
- Syllabus Attendance Policy
- COVID-19 Screening and Reporting Tool
- COVID-19 Curbside Testing
[Important Coronavirus-Related Information] [Table of Contents] [Top]
Homework Assignments
TBA
[Homework Assignments] [Table of Contents] [Top]
Computational Learning Theory Resources
Books
The two main books that we plan to use for the course are available for free in electronic format in the following links:
- Understanding Machine Learning, by Shai Shalev-Shwartz and Shai Ben-David.
- Foundations of Machine Learning, by Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar.
Another book that I like a lot and recommend to people who are starting with machine learning is the following one:
- Machine Learning, by Tom Mitchell.
Personal Notes
Papers
- Queries and Concept Learning, by Dana Angluin.
[Computational Learning Theory Resources] [Table of Contents] [Top]
Class Log
A log for the class will be held online here.
Class 1 (Aug 24, 2020)
Discussion on syllabus and policies.
Mentioned the existence of the following handouts:
- Tools for Bounding Probabilities — a simple collection of bounds that can prove to be useful on probabilistic arguments.
- Basic Tools and Techniques for Algorithms in Learning Theory — contains basic knowledge from probability theory, applications, a rather simple approach on PAC algorithms and a historical overview. Please read Section 3 and perhaps re-read it when we start discussing PAC learning later in the course.
- Essentials on the Analysis of Randomized Algorithms — perhaps the most important and related part to our course is Section 3 which also covers the coupon collector problem.
Discussion of coupon collector's problem. We derived the expected running time and gave an upper bound on the running time (with high probability) using Markov's inequality.
There is still discussion that we should do here next time.
Class 2 (Aug 26, 2020)
Continued our discussion on coupon collection.
Started discussion on terminology that we will be using.
Class 3 (Aug 28, 2020)
TBA.
Class 4 (Aug 31, 2020)
TBA.
Class 5 (Sep 2, 2020)
TBA.
Class 6 (Sep 4, 2020)
TBA.
Class 7 (Sep 7, 2020)
TBA.
Class 8 (Sep 9, 2020)
TBA.
Class 9 (Sep 11, 2020)
TBA.
Class 10 (Sep 14, 2020)
TBA.
Class 11 (Sep 16, 2020)
TBA.
Class 12 (Sep 18, 2020)
TBA.
Class 13 (Sep 21, 2020)
TBA.
Class 14 (Sep 23, 2020)
TBA.
Class 15 (Sep 25, 2020)
TBA.
Class 16 (Sep 28, 2020)
TBA.
Class 17 (Sep 30, 2020)
TBA.
Class 18 (Oct 2, 2020)
TBA.
Class 19 (Oct 5, 2020)
TBA.
Class 20 (Oct 7, 2020)
TBA.
Class 21 (Oct 9, 2020)
TBA.
Class 22 (Oct 12, 2020)
TBA.
Class 23 (Oct 14, 2020)
TBA.
Class 24 (Oct 16, 2020)
TBA.
Class 25 (Oct 19, 2020)
TBA.
Class 26 (Oct 21, 2020)
TBA.
Class 27 (Oct 23, 2020)
TBA.
Class 28 (Oct 26, 2020)
TBA.
Class 29 (Oct 28, 2020)
TBA.
Class 30 (Oct 30, 2020)
TBA.
Class 31 (Nov 2, 2020)
TBA.
Class 32 (Nov 4, 2020)
TBA.
Class 33 (Nov 6, 2020)
TBA.
Class 34 (Nov 9, 2020)
TBA.
Class 35 (Nov 11, 2020)
TBA.
Class 36 (Nov 13, 2020)
TBA.
Class 37 (Nov 16, 2020)
TBA.
Class 38 (Nov 18, 2020)
TBA.
Class 39 (Nov 20, 2020)
TBA.
Class 40 (Nov 23, 2020)
TBA.
Nov 25, 2020
Thanksgiving; no classes.
Nov 27, 2020
Thanksgiving; no classes.
Class 41 (Nov 30, 2020)
TBA.
Class 42 (Dec 2, 2020)
TBA.
Class 43 (Dec 4, 2020)
TBA.
Class 44 (Dec 7, 2020)
TBA.
Class 45 (Dec 9, 2020)
TBA.
Class 46 (Dec 11, 2020)
TBA.
Tuesday, December 15, 2020 (8:00am – 10:00am)
Final exam. In-class (Devon Energy Hall 0120 — where we met throughout the semester).
[Class Log] [Table of Contents] [Top]
