94 citations · 270 across the 17 of their papers we have counts for
19 papers
Decision-aid or Controller? Steering Human Decision Makers with Algorithms
Ruqing Xu, Sarah Dean
Algorithms are used to aid human decision makers by making predictions and recommending decisions. Currently, these algorithms are trained to optimize prediction accuracy. What if…
Perception-Based Sampled-Data Optimization of Dynamical Systems
Liliaokeawawa Cothren, Gianluca Bianchin, Sarah Dean +1
Motivated by perception-based control problems in autonomous systems, this paper addresses the problem of developing feedback controllers to regulate the inputs and the states of a…
Reward Reports for Reinforcement Learning
Thomas Krendl Gilbert, Nathan Lambert, Sarah Dean +2
Building systems that are good for society in the face of complex societal effects requires a dynamic approach. Recent approaches to machine learning (ML) documentation have demons…
Choices, Risks, and Reward Reports: Charting Public Policy for Reinforcement Learning Systems
Thomas Krendl Gilbert, Sarah Dean, Tom Zick +1
In the long term, reinforcement learning (RL) is considered by many AI theorists to be the most promising path to artificial general intelligence. This places RL practitioners in a…
Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability
Mihaela Curmei, Sarah Dean, Benjamin Recht
In this work, we consider how preference models in interactive recommendation systems determine the availability of content and users' opportunities for discovery. We propose an ev…
Axes for Sociotechnical Inquiry in AI Research
Sarah Dean, Thomas Krendl Gilbert, Nathan Lambert +1
The development of artificial intelligence (AI) technologies has far exceeded the investigation of their relationship with society. Sociotechnical inquiry is needed to mitigate the…
AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks
McKane Andrus, Sarah Dean, Thomas Krendl Gilbert +2
Despite interest in communicating ethical problems and social contexts within the undergraduate curriculum to advance Public Interest Technology (PIT) goals, interventions at the g…
Do Offline Metrics Predict Online Performance in Recommender Systems?
Karl Krauth, Sarah Dean, Alex Zhao +4
Recommender systems operate in an inherently dynamical setting. Past recommendations influence future behavior, including which data points are observed and how user preferences ch…
Towards Robust Data-Driven Control Synthesis for Nonlinear Systems with Actuation Uncertainty
Andrew J. Taylor, Victor D. Dorobantu, Sarah Dean +3
Modern nonlinear control theory seeks to endow systems with properties such as stability and safety, and has been deployed successfully across various domains. Despite this success…
Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions
Sarah Dean, Andrew J. Taylor, Ryan K. Cosner +2
Modern nonlinear control theory seeks to develop feedback controllers that endow systems with properties such as safety and stability. The guarantees ensured by these controllers o…
Certainty Equivalent Perception-Based Control
Sarah Dean, Benjamin Recht
In order to certify performance and safety, feedback control requires precise characterization of sensor errors. In this paper, we provide guarantees on such feedback systems when…
Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning
Esther Rolf, Max Simchowitz, Sarah Dean +4
While real-world decisions involve many competing objectives, algorithmic decisions are often evaluated with a single objective function. In this paper, we study algorithmic polici…
Recommendations and User Agency: The Reachability of Collaboratively-Filtered Information
Sarah Dean, Sarah Rich, Benjamin Recht
Recommender systems often rely on models which are trained to maximize accuracy in predicting user preferences. When the systems are deployed, these models determine the availabili…
Robust Guarantees for Perception-Based Control
Sarah Dean, Nikolai Matni, Benjamin Recht +1
Motivated by vision-based control of autonomous vehicles, we consider the problem of controlling a known linear dynamical system for which partial state information, such as vehicl…
Safely Learning to Control the Constrained Linear Quadratic Regulator
Sarah Dean, Stephen Tu, Nikolai Matni +1
We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques. We present a fra…
A Broader View on Bias in Automated Decision-Making: Reflecting on Epistemology and Dynamics
Roel Dobbe, Sarah Dean, Thomas Gilbert +1
Machine learning (ML) is increasingly deployed in real world contexts, supplying actionable insights and forming the basis of automated decision-making systems. While issues result…
Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator
Sarah Dean, Horia Mania, Nikolai Matni +2
We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the…
Delayed Impact of Fair Machine Learning
Lydia T. Liu, Sarah Dean, Esther Rolf +2
Fairness in machine learning has predominantly been studied in static classification settings without concern for how decisions change the underlying population over time. Conventi…
On the Sample Complexity of the Linear Quadratic Regulator
Sarah Dean, Horia Mania, Nikolai Matni +2
This paper addresses the optimal control problem known as the Linear Quadratic Regulator in the case when the dynamics are unknown. We propose a multi-stage procedure, called Coars…