Probabilitas Seminar: Alex Damian
Date and Time
Location
The Probabilitas Seminar series focuses on high-dimensional problems that combine statistics, probability, artificial intelligence, information theory, computer science, and other related fields. The upcoming seminar takes place on Tuesday, October 28, at 1:30pm in Science Center 705. This week's speaker will be Alex Damian, research fellow at the Harvard Kempner Institute.
Learning From Gaussian Data: Single and Multi-Index Models
Abstract: In this work we consider generic Gaussian Multi-index models, in which the labels only depend on the (Gaussian) d-dimensional inputs through their projection onto a low-dimensional subspace, and we study efficient agnostic estimation procedures for this hidden subspace. We introduce the generative leap exponent k*, a natural extension of the generative exponent from [DPVLB24] to the multi-index setting. We first show that a sample complexity of n= Θ(d^{1∨k*/2}) is necessary in the class of algorithms captured by the Low-Degree-Polynomial framework. We then establish that this sample complexity is also sufficient, by giving an agnostic sequential estimation procedure (that is, requiring no prior knowledge of the multi-index model) based on a spectral U-statistic over appropriate Hermite tensors. We further compute the generative leap exponent for several examples including piecewise linear functions (deep ReLU networks with bias).
Topic: Alex Damian seminar
Time: Oct 28, 2025 01:30 PM Eastern Time (US and Canada)
Join Zoom meeting
https://harvard.zoom.us/j/99056003111?pwd=YU5U1HRRj6PXTNTJrUd1zZin3JKH2N.1
Password: 466150
Join by telephone (use any number to dial in)
+1 305 224 1968
+1 309 205 3325
+1 312 626 6799
+1 646 931 3860
+1 929 436 2866
+1 301 715 8592
+1 253 215 8782
+1 346 248 7799
+1 360 209 5623
+1 386 347 5053
+1 507 473 4847
+1 564 217 2000
+1 669 444 9171
+1 669 900 6833
+1 689 278 1000
+1 719 359 4580
+1 253 205 0468
International numbers available: https://harvard.zoom.us/u/abUd6aJDo
One tap mobile: +13052241968,,99056003111# US
Join by SIP conference room system
Meeting ID: 990 5600 3111