Speaker: Rocco Anthony Servedio - Columbia UniversityTitle: Sparsifying suprema of Gaussian processesAbstract: We show that the supremum of any centered Gaussian process can be approximated to any arbitrary accuracy by a finite dimensional Gaussian process, where the dimension of the approximator is just dependent on the target error. As a corollary, we show that for any norm \Phi defined over R^n and target error \eps, there is a norm \Psi such that (i) \Psi is only dependent on t(\eps) = \exp (\exp (poly(1/\eps))) dimensions and (ii) \Psi(x)/\Phi(x) \in [1-\eps, 1+ \eps] with probability 1-\eps (when x is sampled from the Gaussian space). We prove a similar-in-spirit result for sparsifying high-dimensional polytopes in Gaussian space, and present applications to computational learning and property testing. Our proof relies on Talagrand's majorizing measures theorem.Joint work with Anindya De, Shivam Nadimpalli, and Ryan O'Donnell.

What: Sky’s The Limit: a Thriving Stars career panel featuring four accomplished alumnae of the MIT EECS PhD program:Warah Inam SM ’13, PhD ’16 Founder, CEO OverjetRadhika Marathe SM ’11, PhD ’15 LIDAR Design Engineer, Analog DevicesShirin Farrahi SM ’10, PhD ’13 Principal Software Engineer, Cadence Design SystemsSerena Booth SM ’20, PhD ’24 AAAS AI Policy Fellow, US Senate Incoming Asst. Professor, Computer Science, Brown UniversityModerated by Leslie Kolodziejski, Graduate officer and Professor of Electrical Engineering in EECSWhen: Thursday, February 13th from 4 – 5:30 PM EST. Registrants will be reminded of event, and Zoom link is below. Please register in advance right here!Where: On Zoom! We’ll open the platform around 3:45 PM EST. Zoom link: https://mit.zoom.us/j/91700544341Questions? Please contact eecs-thriving-stars@mit.edu

Sid Kankanala (University of Chicago)

Limited Memory and Stochastic Choice | Drew Fudenberg

Join MIT Science Policy Initiative’s (SPI) spring ‘25 kick-off social (w/ dinner!) to learn about our various initiatives – including multiple trips to DC – and meet others with similar interests. Please share the invite with anyone who you think might be interested. Everyone is welcome, even if this is your first event.