CMDS - Reese Pathak

Name: CMDS - Reese Pathak
Start: 2026-11-17T22:00:00+00:00
End: 2026-11-17T23:00:00+00:00
Location: Blocker Building

Make a free account to save this and get a reminder before it starts.Sign up

When: Tuesday, November 17, 20264:00 PM – 5:00 PM CSTAdd to calendar Google Calendar
Where: Blocker BuildingBlocker BuildingOpen in Maps
Hosted by: Department of Mathematics

Reminders arrive as notifications from the NextToU iPhone app. Get the app

Academic & StudyComputer Science & Tech

About

ABSTRACT

Minimizing a loss over a set of data points is ubiquitous in data science. A complete understanding of which loss to minimize, however,

is lacking. This talk focuses on an extremely simple model: estimating an unknown mean corrupted by Gaussian noise. An intuitive

guess is that minimizing square loss (equivalently, maximizing the likelihood) over the parameter space would be the best estimator

possible. Counterintuitively, this is suboptimal in general. Embarrassingly, the reasons for why this occurs are not fully understood! I will

explain some reasons why this can happen, what can be done about it, and some related results around this theme. Based on several

papers, joint with Liviu Aoloritei (UC Berkeley), Cong Ma (U. Chicago), Michael I. Jordan (UC Berkeley/INRIA), Annie Ulichney (UC

Berkeley), and Nikita Zhivotovskiy (UC Berkeley).

Open the original listing

This event is organized by Department of Mathematics, not by NextToU. Details come from a public Texas A&M event listing and may change — check the original event for the latest information.