tl;dr -- Students: please add yourselves to the Piazza page for the class! We will use Piazza extensively.
This course presents some fundamental algorithmic approaches in data science. The approach will be mathematical/algorithmic and proof-based, but attention will be drawn regularly to real-world data-science concerns that motivate our problems and approaches.
Topics include: probability review; data verification on the cloud; hashing, concentration bounds, and Bloom filters; sketching and streaming; Nelson-Yu approximate counting; high-dimensional geometry; dimension reduction and the Johnson-Lindenstrauss Lemma; linear-algebra review; PCA; low-rank approximation; SVD; spectral clustering; gradient descent and its relatives; differential privacy; fairness in data science, and related topics.
There will be a combination of written homeworks (about six), a midterm exam, and a comprehensive final exam.
All homework is to be done individually, but discussions with classmates are encouraged: just list the classmates you discussed the assignment with.
Weight of assignments: homework (45% total), midterm exam (20%), and final exam (35%).
The mid-term will be 11AM-12:15PM on Thursday, March 17th; the final exam 8-10AM on Thursday, May 12. Both will be in class.
Unless otherwise noted, the following late policy shall be applied to all homework:
President Pines provided clear expectations to the University about the wearing of masks for students, faculty, and staff. Face coverings over the nose and mouth are required while you are indoors at all times. KN95 masks are required in all classroom settings and recommended everywhere. There are no exceptions when it comes to classrooms, laboratories, and campus offices. Students not wearing a mask will be given a warning and asked to wear one, or will be asked to leave the room immediately. Students who have additional issues with the mask expectation after a first warning will be referred to the Office of Student Conduct for failure to comply with a directive of University officials.
Please see the Masking mandate at https://umd.edu/virusinfo/emails/080621.
For COVID-19--related Disability Accommodations & Requests for Consideration, see https://umd.edu/virusinfo/emails/063021-2.
The policy on excused absences is at https://www.ugst.umd.edu/V-1.00(G).html.
Please see the university's policies on various important issues.