Sarah Dean

sarahdean AT eecs DOT berkeley DOT edu

Sarah Dean

I am a PhD student in EECS at UC Berkeley, working with Ben Recht and affiliated with BAIR and BCCI. I am funded by a Berkeley fellowship and the NSF graduate research fellowship.* I am interested in the interplay between optimization and learning, and I work specifically on topics in optimal control, machine learning, and computational imaging. I am a founding member of Graduates for Engaged and Extended Scholarship in computing and Engineering (GEESE).

I graduated from the University of Pennsylvania in 2016, where I studied electrical engineering and math and had the pleasure of working with professors Daniel Lee and Daniel Koditschek. During my time at Penn, I worked as a teaching assistant for several math and engineering courses and became engaged in service learning through my involvement with the West Philadelphia Tutoring Project at Civic House. I grew up in upstate New York, and I like to spend my time pretending to be athletic outside: hiking, biking, swimming, sailing, and cross country skiing.


On the Sample Complexity of the Linear Quadratic Regulator [arXiv]
Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, and Stephen Tu
accepted with minor revisions to FoCM.

Delayed Impact of Fair Machine Learning [arXiv] [Bloomberg] [BAIR Blog]
Lydia T. Liu, Sarah Dean, Esther Rolf, Max Simchowitz, and Moritz Hardt
Best Paper Award at ICML 2018.

A Broader View on Bias in Automated Decision-Making: Reflecting on Epistemology and Dynamics [arXiv]
Roel Dobbe, Sarah Dean, Thomas Gilbert, and Nitin Kohli
presented at FAT/ML 2018.

Optimal Path and Illumination Design for Multiframe Motion Deblurring [summary]
Sarah Dean, Zachary Phillips, Laura Waller, and Benjamin Recht
presented at OSA Imaging and Applied Optics Congress 2018,
awarded Best Student Paper in Imaging Systems.

Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator [arXiv] [github]
Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, and Stephen Tu
to appear at NIPS 2018.

Safely Learning to Control the Constrained Linear Quadratic Regulator [arXiv]
Sarah Dean, Stephen Tu, Nikolai Matni, and Benjamin Recht
under review.

*I have made my application available for reference here.

a woman among giants
Last updated 26 September 2018.