Sarah Dean

About Me  •   Teaching  •   Advising  •   Publications

Sarah Dean

sdean AT cornell DOT edu

I am an Assistant Professor in the CS Department at Cornell. I can't guarantee a reply to every email. I do not have the capacity to supervise remote internships.

I study the interplay between optimization, machine learning, and dynamics in real-world systems. My research focuses on understanding the fundamentals of data-driven methods for control and decision-making, inspired by applications ranging from robotics to recommendation systems. You can learn more by reading my dissertation or watching my dissertation talk.

In fall 2021, I was a postdoc with Jamie Morgenstern at UW. Before that, I was a PhD student in EECS at UC Berkeley, advised by Ben Recht. At Berkeley, I was a founding member of Graduates for Engaged and Extended Scholarship in computing and Engineering (GEESE). I interned with Canopy in Boston, MA during Summer 2019. For reference, my job talk, CV, faculty app, and NSF GRFP app.


At Cornell, I am teaching CS 4/5789: Introduction to Reinforcement Learning in Spring 2024 (previously in 2022, 2023). I taught Machine Learning in Feedback Systems (CS 6784) in Fall 2023 (previously in 2022).

At Berkeley, I worked on course development for a new EECS Anti-Racism and Social Justice course (and gave a guest lecture on Bias in Algorithms) and as a Graduate Student Instructor for Statistical Learning Theory (EECS 281) and Introduction to Machine Learning (EECS 189/289).

Advising and Mentoring

I've had the pleasure of working with several students at Cornell, including PhD advisees Kimia Kazemian, Raunak Kumar (co-advised with Bobby Kleinberg), and Rohan Banerjee (co-advised with Tapo Bhattacharjee); undergraduates Vadim Popov (2023), Rachael Close (2023), Amelia Kovacs (2022-present), Alexis Hao (2022), Emily Mei (2022), Fengyu Li (2022), Jiwoo Cheon (2022).


My Google Scholar profile has the most up to date list of publications and preprints. If you are interested in code for a paper without a github link, feel free to send me an email.

Strategic Usage in a Multi-Learner Setting [arXiv] [github]
Eliot Seo Shekhtman, Sarah Dean.
to appear at AISTATS 2024.
short version presented (oral) at AAAI 2024 Recommendation Ecosystems Workshop: Modeling, Optimization, and Incentive Design.

Random Features Approximation for Control-Affine Systems
Kimia Kazemian, Yahya Sattar, Sarah Dean.
to appear at L4DC 2024.
short version presented at NeurIPS Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems 2023.

To Ask or Not To Ask: Robot-assisted Bite Acquisition with Human-in-the-loop Contextual Bandits [openreview]
Rohan Banerjee, Sarah Dean, Tapomayukh Bhattacharjee.
presented at First Workshop on Out-of-Distribution Generalization in Robotics at CoRL 2023.

Initializing Services in Interactive ML Systems for Diverse Users [arXiv]
Avinandan Bose, Mihaela Curmei, Daniel L. Jiang, Jamie Morgenstern, Sarah Dean, Lillian J.Ratliff, Maryam Fazel.
in submission.

Emergent segmentation from participation dynamics and multi-learner retraining [arXiv] [slides] [talk]
Sarah Dean, Mihaela Curmei, Lillian J. Ratliff, Jamie Morgenstern, and Maryam Fazel
to appear at AISTATS 2024.

Ranking with Long-Term Constraints [arXiv] [github]
Kianté Brantley, Zhichong Fang, Sarah Dean, Thorsten Joachims
presented at WSDM 2024.

Online Convex Optimization with Unbounded Memory [arXiv] [slides]
Raunak Kumar, Sarah Dean, Robert D. Kleinberg
presented at NeuRIPS 2023.

Reward Reports for Reinforcement Learning [arXiv]
Thomas Krendl Gilbert, Sarah Dean, Nathan Lambert, Tom Zick, and Aaron Snoswell
presented at AIES 2023.
short version at Responsible Decision Making in Dynamic Environments workshop at ICML 2022.

Perception-Based Sampled-Data Optimization of Dynamical Systems [arXiv]
Liliaokeawawa Cothren, Gianluca Bianchin, Sarah Dean, Emiliano Dall'Anese
presented at IFAC 2023.

Modeling Content Creator Incentives on Algorithm-Curated Platforms [arXiv] [overview]
Jiri Hron, Karl Krauth, Michael I. Jordan, Niki Kilbertus, and Sarah Dean
oral presentation at ICLR 2023.

Engineering a Safer Recommender System [PDF]
Liu Leqi and Sarah Dean
at Responsible Decision Making in Dynamic Environments workshop at ICML 2022.

Preference Dynamics Under Personalized Recommendations [arXiv] [slides] [talk]
Sarah Dean and Jamie Morgenstern
presented at EC 2022.

Choices, Risks, and Reward Reports: Charting Public Policy for Reinforcement Learning Systems [CLTC] [arXiv]
Thomas Krendl Gilbert, Sarah Dean, Tom Zick, and Nathan Lambert
Center for Long-Term Cybersecurity Whitepaper Series (2022).

Towards Robust Data-Driven Control Synthesis for Nonlinear Systems with Actuation Uncertainty [arXiv]
Andrew J. Taylor*, Victor D. Dorobantu*, Sarah Dean*, Benjamin Recht, Yisong Yue, and Aaron D. Ames
presented at CDC 2021.

Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability [arXiv]
Mihaela Curmei*, Sarah Dean*, and Benjamin Recht
presented at ICML 2021,
short version presented at Participatory Approaches to Machine Learning workshop at ICML 2020.

Certainty Equivalent Perception-Based Control [arXiv] [github] [talk] [slides]
Sarah Dean and Benjamin Recht
oral presentation at L4DC 2021.

Axes for Sociotechnical Inquiry in AI Research [arXiv] [IEEE]
Sarah Dean, Thomas Krendl Gilbert, Nathan Lambert, and Tom Zick
published in IEEE Transactions on Technology and Society (2021).

AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks [arXiv]
McKane Andrus, Sarah Dean, Thomas Krendl Gilbert, Nathan Lambert, and Tom Zick
presented at IEEE ISTAS 2020.

Do Offline Metrics Predict Online Performance in Recommender Systems? [arXiv] [github]
Karl Krauth, Sarah Dean*, Alex Zhao*, Wenshuo Guo*, Mihaela Curmei*, Benjamin Recht, and Michael I. Jordan
presented at the Workshop on Consequential Decisions in Dynamic Environments at NeurIPS 2020.

Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions [arXiv] [video] [talk] [slides] [github]
Sarah Dean, Andrew Taylor, Ryan Cosner, Benjamin Recht, and Aaron Ames
Best Paper Finalist at CoRL 2020.

Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning [arXiv] [github]
Esther Rolf, Max Simchowitz, Sarah Dean, Lydia T Liu, Daniel Björkegren, Moritz Hardt, and Joshua Blumenstock
presented at ICML 2020,
short version awarded Best Paper at NeurIPS Joint Workshop on AI for Social Good 2019.

Robust Guarantees for Perception-Based Control [arXiv] [slides] [talk] [poster] [github]
Sarah Dean, Nikolai Matni, Benjamin Recht, and Vickie Ye
presented at L4DC 2020.

Recommendations and User Agency: The Reachability of Collaboratively-Filtered Information [arXiv] [talk]
Sarah Dean, Sarah Rich, and Benjamin Recht
presented at FAccT 2020.

On the Sample Complexity of the Linear Quadratic Regulator [arXiv] [FoCM] [talk]
Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, and Stephen Tu
published in Foundations of Computational Mathematics (2019).

High-throughput fluorescence microscopy using multi-frame motion deblurring [BOE] [github]
Zachary Phillips, Sarah Dean, Laura Waller, and Benjamin Recht
published in Biomedical Optics Express 11 (2020),
extended abstract awarded Best Student Paper in Imaging Systems at OSA Congress 2018.

Safely Learning to Control the Constrained Linear Quadratic Regulator [arXiv] [slides]
Sarah Dean, Stephen Tu, Nikolai Matni, and Benjamin Recht
presented at ACC 2019.

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

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.

Last updated December 2023.

a woman among giants