EECS Special Seminar: Karan Singh "Provably Robust Algorithms for Prediction and Control"

Speaker: Karan Singh , Microsoft Research Redmond

Date: Thursday, April 07, 2022

Time: 10:00 AM to 11:00 AM Note: all times are in the Eastern Time Zone

Public: Yes

Location: changed to Zoom only:

Event Type: Seminar

Room Description:

Host: Pablo Parrilo

Contact: Fern D Keniston,

Relevant URL:

Speaker URL: None

Speaker Photo:
Karan singh headshot

Reminders to:

Reminder Subject: TALK: EECS Special Seminar: Karan Singh "Provably Robust Algorithms for Prediction and Control"

Feedback-driven decision-making systems are at the emerging frontier of machine learning applications. Upcoming applications of societal consequence, such as self-driving vehicles and smartwatch-based health interventions, have to contend with the challenge of operating in reactive stateful environments. In this talk, I will describe my work on designing principled robust algorithms for feedback-driven learning, with provable guarantees on computational and statistical efficiency.

First, I will introduce an efficient instance-optimal algorithm for control in the presence of adversarial disturbances. Beyond the realm of both stochastic and robust control, such a data-driven notion of optimality combines worst-case guarantees with a promise of exceptional performance on benign instances. Moving on to prediction, I will present a computationally and statistically efficient forecasting strategy for latent-state dynamical systems exhibiting long term dependencies, mitigating the statistical challenge of learning with correlated samples, and the computational difficulties associated with a non-convex maximum likelihood objective. To conclude, I will discuss some practically relevant fundamental questions at the intersection of machine learning, optimization, and control that have the potential to unlock real progress in downstream applications.

Karan Singh is a postdoctoral researcher at Microsoft Research Redmond. In November 2021, he completed his PhD in Computer Science at Princeton University, where he was awarded the Porter Ogden Jacobus Fellowship, Princeton University's highest graduate student honor. Karan's research addresses statistical and computational challenges in feedback-driven interactive learning, spanning both prediction and control. His results draw from the algorithmic toolkits of optimization and online learning, together with techniques from dynamical systems and control theory.

Research Areas:

Impact Areas:

This event is not part of a series.

Created by Fern D Keniston Email at Saturday, April 02, 2022 at 3:28 PM.