Theory Lunch Seminar - Shivam Nadimpalli

— 1:00pm

Location:
In Person - Gates Hillman 8102

Speaker:
SHIVAM NADIMPALLI, Instructor in Applied Mathematics, Department of Mathematics, Massachusetts Institute of Technology
https://math.mit.edu/~shivamn/

We study the approximability of high-dimensional convex sets by intersections of halfspaces, where the approximation quality is measured with respect to the standard Gaussian distribution and the complexity of an approximation is the number of halfspaces used.

We establish a range of upper and lower bounds both for general convex sets and for specific natural convex sets that are of particular interest. We rely on techniques from many different areas, including classical results from convex geometry, Cramér-type bounds from probability theory, and—perhaps surprisingly—a range of topics from computational complexity theory, including computational learning theory, unconditional pseudorandomness, and the study of influences and noise sensitivity in the analysis of Boolean functions.

Based on joint work  with Anindya De and Rocco Servedio.

Event Website:
https://www.cs.cmu.edu/~theorylunch/abstractsHTML/20250205.html


Add event to Google
Add event to iCal