Shane T. Barratt

About me

alt text 

Ph.D. candidate,
Electrical Engineering, Stanford University
E-mail: stbarratt [@] gmail [dot] com

I am currently working towards the Ph.D. degree in electrical engineering at Stanford University, advised by Professor Stephen Boyd. My research focuses on convex optimization, and in particular its applications to machine learning and control. I received the M.S. degree in electrical engineering from Stanford University, in 2019, and the B.S. degree in electrical engineering and computer science from the University of California, Berkeley, in 2017. Previously, I have interned at Blackrock, Lyft Level 5 (see the blog post), Google (in particular, Skybox Imaging/Terra Bella), Qualcomm-Atheros, and SoRoCo. This fall, I am consulting for Blackrock and the SF Giants.


For papers listed by citation count, see Google Scholar. * denotes equal contribution.


Low rank forecasting (code)

S. Barratt, Y. Dong, and S. Boyd. Manuscript.

Learning convex optimization models (code)

A. Agrawal, S. Barratt, and S. Boyd*. Manuscript.

Optimal representative sample weighting (code)

S. Barratt, G. Angeris, and S. Boyd. Manuscript.

Multi-period liability clearing via convex optimal control (code)

S. Barratt and S. Boyd. Manuscript.

Learning convex optimization control policies (PMLR version, code, talk)

A. Agrawal, S. Barratt, S. Boyd, and B. Stellato*. 2020 Conference on Learning for Dynamics and Control (L4DC), Oral.

Fitting a linear control policy to demonstrations with a Kalman constraint (PMLR version, code)

M. Palan, S. Barratt*, A. McCauley, D. Sadigh, V. Sindhwani, and S. Boyd. 2020 Conference on Learning for Dynamics and Control (L4DC), Poster.

Convex optimization over risk-neutral probabilities (code)

S. Barratt, J. Tuck, and S. Boyd. Manuscript.

Minimizing a sum of clipped convex functions (code)

S. Barratt, G. Angeris, and S. Boyd. To appear, Optimization Letters.

Least squares auto-tuning (code)

S. Barratt and S. Boyd. To appear, Engineering Optimization.

Automatic repair of convex optimization problems (code)

S. Barratt, G. Angeris, and S. Boyd. Optimization & Engineering.

Fitting a Kalman smoother to data (code, talk)

S. Barratt and S. Boyd. 2020 American Control Conference.


Differentiable convex optimization layers (code)

A. Agrawal, B. Amos, S. Barratt, S. Boyd, S. Diamond, Z. Kolter*. 2019 Neural Information Processing Systems (NeurIPS).

Learning probabilistic trajectory models of aircraft in terminal airspace from position data (code)

S. Barratt, M. Kochenderfer, and S. Boyd. IEEE Transactions on Intelligent Transportation Systems.

A distributed method for fitting Laplacian regularized stratified models (code, talk)

J. Tuck, S. Barratt, and S. Boyd. Manuscript.

Differentiating through a cone program (code)

A. Agrawal, S. Barratt, S. Boyd, E. Busseti, and W. Moursi*. Journal of Applied and Numerical Optimization.


Stochastic control with affine dynamics and extended quadratic costs (code)

S. Barratt and S. Boyd. Manuscript.

Direct model predictive control

S. Barratt. ICML 2018 Workshop on Planning and Learning.

A note on the inception score

S. Barratt, R. Sharma*. ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models.

Improved training with curriculum GANs

R. Sharma, S. Barratt, S. Ermon, and V. Pande. Manuscript.


Cooperative multi-agent reinforcement learning for low-level wireless communication

C. de Vrieze, S. Barratt, D. Tsai, and A. Sahai. Manuscript.

InterpNET: neural introspection for interpretable deep learning

S. Barratt. Interpretable ML Symposium, 2017 Neural Information Processing Systems (NeurIPS).


A non-rigid point and normal registration algorithm with applications to learning from demonstrations (videos)

A. Lee, M. Goldstein, S. Barratt, and P. Abbeel. 2015 International Conference on Robotics and Automation (ICRA).