Gautam Goel

Department of Computing & Mathematical Sciences
California Institute of Technology

Email: ggoel@caltech.edu


I am a PhD student in the Computing and Mathematical Sciences (CMS) department at Caltech, where I am extremely fortunate to be advised by Babak Hassibi. I am broadly interested in machine learning, optimization, and control, especially 1) online optimization and sequential decision-making under uncertainty, and 2) integrating machine learning with dynamics and control. Much of my PhD work has been supported by a National Science Foundation Graduate Research Fellowship and an Amazon AI4Science Fellowship.

In Fall 2022 I will join UC Berkeley as a postdoctoral scholar hosted by the Foundations of Data Science Institute.

For more information, please see my CV.


Papers. Sorted in decreasing chronological order.

  1. Online estimation and control with optimal pathlength regret with Babak Hassibi. Learning for Dynamics and Control (L4DC) 2022.

  2. Competitive Control with Babak Hassibi. Transactions of Automatic Control (TAC).

  3. The Power of Linear Controllers in LQR Control with Babak Hassibi. Preprint.

  4. Regret-Optimal Estimation and Control with Babak Hassibi. Transactions of Automatic Control (TAC) (Special Issue on Learning and Control).

  5. Regret-Optimal Full-Information Control with Oron Sabag, Sahin Lale, and Babak Hassibi. American Control Conference (ACC) 2021.

  6. Regret-Optimal Measurement-Feedback Control with Babak Hassibi. Learning for Dynamics and Control (L4DC) 2021.

  7. Online Optimization with Predictions and Non-convex Losses with Yiheng Lin and Adam Wierman. Sigmetrics 2020.

  8. Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization with Yiheng Lin. Haoyuan Sun, and Adam Wierman. NeurIPS 2019 (Spotlight Presentation).

  9. An Online Algorithm for Smoothed Regression and LQR Control with Adam Wierman. AISTATS 2019.

  10. Smoothed Online Convex Optimization in High Dimensions via Online Balanced Descent with Niangjun Chen and Adam Wierman. COLT 2018.

  11. Thinking Fast and Slow: Optimization Decomposition across Timescales with Niangjun Chen and Adam Wierman. Conference on Decision and Control (CDC) 2017.