Gautam Goel



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 AWS AI Fellowship. In 2021 I was named a Rising Star in Data Science by the University of Chicago Center for Data and Computing.

I enjoy travelling, and have visited the following countries for conferences during my PhD: Australia (CDC 2017), Sweden (COLT 2018), Japan (AISTATS 2019), and Canada (NeurIPS 2019).

For more information, please see my CV.


Contact

ggoel [at] caltech [dot] edu

Gautam Goel
Caltech
1200 E California Blvd
Pasadena, CA 91125


Reviewing

I have reviewed papers for NeurIPS, ICLR, and several IEEE journals, including Transactions on Automatic Control, Transactions on Networking, and Transactions on Information Theory.


Publications

For citation information, please see my Google Scholar profile . (*) denotes equal contribution.

G. Goel, B. Hassibi. Competitive Control. Preprint.

G. Goel, B. Hassibi. Regret-optimal Estimation and Control. Preprint.

G. Goel, B. Hassibi. The Power of Linear Controllers in LQR Control. Preprint.

G. Goel, B. Hassibi. Regret-optimal measurement-feedback control. Learning for Dynamics and Control (L4DC) 2021.

Y. Lin, G. Goel, A. Wierman. Online Optimization with Predictions and Non-convex Losses. Sigmetrics 2020.

G. Goel*, Y. Lin*, H. Sun*, A. Wierman. Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization. NeurIPS 2019. Spotlight presentation (top 2.4% of submssions).

G. Goel, A. Wierman. An Online Algorithm for Smoothed Regression and LQR control. AISTATS 2019.

N. Chen*, G. Goel*, A. Wierman. Smoothed Online Convex Optimization in High Dimensions via Online Balanced Descent. Conference on Learning Theory (COLT) 2018.

G. Goel, N. Chen, A. Wierman. Thinking fast and slow: Optimization decomposition across timescales. Conference on Decision and Control (CDC) 2017.