CMSC 858L, Foundations of Machine Learning, Fall 2015: Tue, Thu
Office: AVW 3263, Phone: 301-405-2695
Instructor's office Hours (starting Sept 3rd): Tue and Thu 10-11 in AVW 3263
(additional slots by appointment; Aravind is happy to talk to students)
Course Time and Location: Tue, Thu
2-3:15PM, CSIC 3120
Half-TA: David G. Harris
Course material and topics: There will be no required textbook for this course: we will primarily use Rob Schapire's excellent scribed course notes. The book by Shalev-Schwartz and Ben-David (also available free online
here) is also very useful.
Based on time available, we also plan to cover additional topics including kernels, basic optimization techniques, information theory, and ethical issues. This being a "foundations" course, the emphasis will be on rigorous
algorithms and proofs; we will also discuss practical heuristics & applications and ethical considerations. Check out
Samuel Ieong's notes and
videos for relevant probability background.
Please click here for the regularly-updated list of topics covered in past classes.
Problem-solving: The best way to learn the material is through problem-solving. We will facilitate this
via a partially-inverted classroom format: since we will closely follow Schapire's notes for
much of the class, students will be expected to read ahead from the notes (read from start to end, a bit ahead of class). We will go over the notes in class faster
than in an introductory graduate class, and use the resultant time to do some problem-solving during Thursday classes.
Homework and Project: We will have some graded and some ungraded
homework assignments. Students will work in groups of three for graded
homework assignments, and are also urged to complete the
ungraded assignments (solutions to which will be provided).
The project will involve reading substantial material and problem-solving based on it;
alternatively, student-groups are welcome to propose to Aravind new projects that they will do based on
the course material -- please make such proposals by October 1st, and Aravind will respond by October 6th
whether your proposal is approved or not.
Grading and participation: We will have a take-home mid-term and in-class
final. The grade will be determined by: Homework 30%, Mid-term 25%,
Final 35%, and Class Project 10%.
Enthusiastic participation is strongly encouraged. Much of the outside-classroom discussion
will be through Piazza; please register and participate.
Exams: The final will be during the university's
official time: in our classroom CSIC 3120, 10:30AM-12:30PM on Thursday,
Dec 17th. The final will include everything covered during the semester: you
can bring your own notes, HW solutions, Schapire's notes, and handouts given in class - no
other material is allowed. The mid-term will be take-home: posted on 10/22, due back by
Qualifying areas: The course will be valid for Ph.D. qualifying coursework,
M.S. qualifying coursework, and M.S. comps, all in the Algorithms and
Computation Theory and AI areas; the relevant exams will be the
mid-term and the final.
General Info.: Class participation is strongly encouraged;
students are urged to come to the office hours if they have questions, and
can also email Aravind to setup alternative times if they cannot attend the
regular office hours. A few lectures will be rescheduled (or covered by
guest lectures) during Aravind's travel; very few of the office hours
may also be canceled. (Again, students are always welcome to email Aravind
to setup additional meeting-times as needed.)
See the university's policy on medically-necessitated absence from class. The
"Major Scheduled Grading Events" for this course are the mid-term and
final exams; students claiming an excused absence from these events
must apply in writing and furnish documentary support (such as from a
health-care professional who treated
the student) for any assertion that the absence qualifies as an excused
absence. The support should explicitly indicate the dates or times the
student was incapacitated due to illness. Self-documentation of illness
is not itself sufficient support to excuse the absence. An instructor
is not under obligation to offer a substitute assignment or to give a
student a make-up assessment unless the failure to perform was due to
an excused absence.
Academic Accommodations for Disabilities
Any student eligible for and requesting reasonable academic accommodations
due to a disability is requested to provide, to the instructor in office
hours, a letter of accommodation from the Office of Disability Support
Services (DSS) within the first two weeks of the semester.
The University of Maryland, College Park has a nationally recognized
Code of Academic Integrity, administered by the Student Honor Council.
This Code sets standards for academic integrity at Maryland for all
undergraduate and graduate students. As a student you are responsible
for upholding these standards for this course. It is very important for
you to be aware of the consequences of cheating, fabrication,
facilitation, and plagiarism. For more information on the Code of
Academic Integrity or the Student Honor Council, please visit
To further exhibit your commitment to academic integrity, remember to
sign the Honor Pledge on all examinations and assignments: "I pledge on
my honor that I have not given or received any unauthorized assistance
on this examination (assignment)."