Time varying regression with hidden linear dynamics

Wednesday, March 16, 2022 - 4:00pm to 4:30pm

Event Calendar Category

LIDS & Stats Tea

Speaker Name

Horia Mania



Building and Room Number

LIDS Lounge


We revisit a model for time-varying linear regression that assumes the unknown parameters evolve according to a linear dynamical system. Counterintuitively, we show that when the underlying dynamics are stable the parameters of this model can be estimated from data by combining just two ordinary least squares estimates. We offer a finite sample guarantee on the estimation error of our method and discuss certain advantages it has over Expectation-Maximization (EM), which is the main approach proposed by prior work.

Joint work with: Ali Jadbabaie, Devavrat Shah, Suvrit Sra


Horia is a postdoctoral associate at MIT, in the Laboratory for Information and Decision Systems. He completed his PhD studies at UC Berkeley under the guidance of Michael I. Jordan and Benjamin Recht, and prior to that he obtained a BA in mathematics from Princeton University. Horia is the winner of the 2021 Eli Jury student award for contributions to control theory. Horia is broadly interested in machine learning and its connections to statistics, optimization, and control theory.