NYU CSGY 9223D (3943B)
Algorithmic Machine Learning
and Data Science
Advanced theory course exploring contemporary algorithmic techniques and recent research on computational methods that enable machine learning and data science at scale.
Course Team:
Administrative Information
Lectures: 370 Jay St., Room 1201 and via Zoom (link on NYU Classes).
Lecture component: Wed. 11:00am12:15pm.
Flipped component: Wed. 12:30pm1:30pm.
Recorded component: Posted Thurs. by EOD.
Syllabus: here. Please see for information on COVID19 changes.
Final project guidelines: here.
Midterm information and practice: here.
Professor Office hours: Thurs. 10am12pm, Zoom link.
Raphael's Undergrad. Office hours: Mon. 122pm, Zoom link.
Paper Reading Group: Mon. 13pm via Zoom (link on NYU Classes).
Piazza: Signup Link.
Student run Slack: Link.
Quizzes: Weekly checkin quizzes will be administered via Google Forms. Link will be posted on this site. They must be completed by 11:00am ET the Wed. after they are posted.
Homework: Homework must be turned in to NYU Classes by the specified due date. While not required, I encourage students to prepare problem sets in LaTeX or Markdown (with math support.) You can use this template for LaTeX. While there is a learning curve for LaTeX (less for Markdown), it typically saves students time by the end of the semester! If you write problems by hand, please scan and upload as a PDF.
Collaboration is allowed on homework, but solutions and any code must be writtenup independently. Writing should not be done in parallel with others. Students must list collaborators on their problem sets (for each problem separately). See the syllabus for full details.
Course Summary
Prerequisites: This course is mathematically rigorous, and is intended for graduate students and advanced undergraduates. Formally we require previous courses in machine learning, algorithm design and analysis, and linear algebra. Experience with probability and random variables is necessary. See the syllabus for more details and email Prof. Musco if you have questions about your preparation for the course!
Coursework: One meeting per week. Short weekly quiz due before next class (10% of grade). Problem sets every two weeks involving analysis and application of algorithmic methods learned in class, with some programming exercises (40% of grade). Athome midterm exam (15% of grade). Final project to be completed in groups of two (25% of grade). Class participation is the remaining 10% of the grade. Please consult the formal syllabus for more information.
Resources: There is no textbook to purchase. Course material will consist of my written lecture notes, as well as assorted online resources, including papers, notes from other courses, and publicly available surveys. Please refer to the course webpage before and after lectures to keep uptodate as new resources are posted.
Optional Reading Group: It's an exciting time for research at the intersection of algorithm design and the data sciences. Most of the topics covered in this course are still the subject of active research. We will hold a reading group where students will present and discuss recent papers (time TBA). This is a great opportunity to learn extra material, learn to read papers, and find a project topic.
Week #  Topic  Reading  Homework  

The Power of Randomness  
1. 9/2 
In class: Concentration of random variables, applications to hashing Supplemental: Load balancing, the union bound. Link. 



9/9  No Class, Monday Schedule for Labor Day  
2. 9/16 
In Class: Sketching and streaming algorithms, MinHash.
Supplemental: Exponential tail bounds (Chernoff + Bernstein) 



3. 9/23 
In class: Highdimensional geometry Supplemental: The JohnsonLindenstrauss lemma + applications 



4. 9/30 
In class: Randomized near neighbor search, analyzing locality sensitive hash functions Supplemental: None 



FirstOrder Optimization  
5. 10/7 
In class: Analyzing gradient descent and project gradient descent for convex problems 



6. 10/14 
In class: Online and stochastic gradient descent 



7. 10/21 
In class: Smoothness, strong convexity, conditioning. 


8. 10/28 
In class: Preconditioning, acceleration, coordinate descent, nonconvex optimization 



Spectral Methods and Linear Algebra  
9. 11/04 
In class: Singular value decomposition, Power Method Supplemental: Krylov subspace methods and a taste of approximation theory 



10. 11/11 
In class: Spectral graph theory and spectral clustering, generative models for networks, stochastic block model 



11. 11/18 
In class: Randomized numerical linear algebra, sketching for linear regression, εnets arguments 


Fourier Methods  
12. 11/25 
In class: Sampling from vectors, Fast JohnsonLindenstrauss 



13. 12/2  In class: Sparse recovery and compresses sensing, restricted isometry property, basis pursuit 


14. 12/9  In class: Leverage scores, spectral sparsifiers, and a taste of my research. 