Portrait of Gautam Goel

Gautam Goel

Simons Institute for the Theory of Computing

University of California, Berkeley

Email: ggoel@berkeley.edu

I am a postdoctoral researcher at the Simons Institute at UC Berkeley, where I am supervised by Peter Bartlett. Previously, I was a PhD student in the Computing and Mathematical Sciences (CMS) department at Caltech, where I was supervised by Babak Hassibi. My thesis was awarded the Bhansali Family Doctoral Prize in Computer Science, which is awarded by the CMS department to a single outstanding dissertation in computer science each year.

My research interests lie in machine learning and optimization. I am particularly interested in i) optimization, generalization, and uncertainty quantification in deep learning, and ii) online learning, reinforcement learning, time-series forecasting, and optimal control.

For more information, please see my CV.

Papers

Sorted in decreasing chronological order.

  1. Can a Transformer Represent a Kalman Filter? with Peter Bartlett. Preprint. [arXiv]
  2. Best of Both Worlds in Online Control: Competitive Ratio and Policy Regret. with Naman Agarwal, Karan Singh, and Elad Hazan. L4DC 2023. [arXiv]
  3. Measurement-Feedback Control with Optimal Data-Dependent Regret. with Babak Hassibi. Preprint. [arXiv]
  4. Online Estimation and Control with Optimal Pathlength Regret. with Babak Hassibi. L4DC 2022. [arXiv]
  5. Competitive Control. with Babak Hassibi. IEEE Transactions on Automatic Control. [arXiv]
  6. The Power of Linear Controllers in LQR Control. with Babak Hassibi. CDC 2022. (Invited Session on Non-Asymptotic Learning and Control of Dynamical Systems). [arXiv]
  7. Regret-Optimal Estimation and Control. with Babak Hassibi. IEEE Transactions on Automatic Control. (Special Issue on Learning and Control). [arXiv]
  8. Regret-Optimal Full-Information Control. with Oron Sabag, Sahin Lale, and Babak Hassibi. ACC 2021. [arXiv]
  9. Regret-Optimal Measurement-Feedback Control. with Babak Hassibi. L4DC 2021. [arXiv]
  10. Online Optimization with Predictions and Non-Convex Losses. with Yiheng Lin and Adam Wierman. SIGMETRICS 2020. [arXiv]
  11. Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization. with Yiheng Lin, Haoyuan Sun, and Adam Wierman. NeurIPS 2019. (Spotlight Presentation). [arXiv]
  12. An Online Algorithm for Smoothed Regression and LQR Control. with Adam Wierman. AISTATS 2019. [arXiv]
  13. Smoothed Online Convex Optimization in High Dimensions via Online Balanced Descent. with Niangjun Chen and Adam Wierman. COLT 2018. [arXiv]
  14. Thinking Fast and Slow: Optimization Decomposition across Timescales. with Niangjun Chen and Adam Wierman. CDC 2017. [arXiv]