Search Results for author: Sarah Dean

Found 25 papers, 13 papers with code

Strategic Usage in a Multi-Learner Setting

1 code implementation29 Jan 2024 Eliot Shekhtman, Sarah Dean

Extensive prior research has been conducted on the effects of strategic users in single-service settings, with strategic behavior manifesting in the manipulation of observable features to achieve a desired classification; however, this can often be costly or unattainable for users and fails to capture the full behavior of multi-service dynamic systems.

Initializing Services in Interactive ML Systems for Diverse Users

no code implementations19 Dec 2023 Avinandan Bose, Mihaela Curmei, Daniel L. Jiang, Jamie Morgenstern, Sarah Dean, Lillian J. Ratliff, Maryam Fazel

(ii) Suboptimal Local Solutions: The total loss (sum of loss functions across all users and all services) landscape is not convex even if the individual losses on a single service are convex, making it likely for the learning dynamics to get stuck in local minima.

Ranking with Long-Term Constraints

1 code implementation10 Jul 2023 Kianté Brantley, Zhichong Fang, Sarah Dean, Thorsten Joachims

The feedback that users provide through their choices (e. g., clicks, purchases) is one of the most common types of data readily available for training search and recommendation algorithms.

Fairness

Decision-aid or Controller? Steering Human Decision Makers with Algorithms

no code implementations23 Mar 2023 RuQing Xu, Sarah Dean

We first consider fixed human decision functions which map observable features and the algorithm's recommendations to final decisions.

Cross-Dataset Propensity Estimation for Debiasing Recommender Systems

no code implementations22 Dec 2022 Fengyu Li, Sarah Dean

Datasets for training recommender systems are often subject to distribution shift induced by users' and recommenders' selection biases.

Causal Inference Quantization +2

Perception-Based Sampled-Data Optimization of Dynamical Systems

no code implementations18 Nov 2022 Liliaokeawawa Cothren, Gianluca Bianchin, Sarah Dean, Emiliano Dall'Anese

Moreover, we show that the interconnected system tracks the solution trajectory of the underlying optimization problem up to an error that depends on the approximation errors of the neural network and on the time-variability of the optimization problem; the latter originates from time-varying safety and performance objectives, input constraints, and unknown disturbances.

Autonomous Driving

Modeling Content Creator Incentives on Algorithm-Curated Platforms

no code implementations27 Jun 2022 Jiri Hron, Karl Krauth, Michael I. Jordan, Niki Kilbertus, Sarah Dean

To this end, we propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets.

Emergent segmentation from participation dynamics and multi-learner retraining

1 code implementation6 Jun 2022 Sarah Dean, Mihaela Curmei, Lillian J. Ratliff, Jamie Morgenstern, Maryam Fazel

We study the participation and retraining dynamics that arise when both the learners and sub-populations of users are \emph{risk-reducing}, which cover a broad class of updates including gradient descent, multiplicative weights, etc.

Preference Dynamics Under Personalized Recommendations

no code implementations25 May 2022 Sarah Dean, Jamie Morgenstern

We use a similar model of preference dynamics, where an individual's preferences move towards content the consume and enjoy, and away from content they consume and dislike.

Reward Reports for Reinforcement Learning

1 code implementation22 Apr 2022 Thomas Krendl Gilbert, Nathan Lambert, Sarah Dean, Tom Zick, Aaron Snoswell

Building systems that are good for society in the face of complex societal effects requires a dynamic approach.

Chatbot reinforcement-learning +1

Choices, Risks, and Reward Reports: Charting Public Policy for Reinforcement Learning Systems

1 code implementation11 Feb 2022 Thomas Krendl Gilbert, Sarah Dean, Tom Zick, Nathan Lambert

In the long term, reinforcement learning (RL) is considered by many AI theorists to be the most promising path to artificial general intelligence.

Recommendation Systems reinforcement-learning +1

Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability

1 code implementation30 Jun 2021 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.

Recommendation Systems

AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks

no code implementations4 Feb 2021 McKane Andrus, Sarah Dean, Thomas Krendl Gilbert, Nathan Lambert, Tom Zick

Despite interest in communicating ethical problems and social contexts within the undergraduate curriculum to advance Public Interest Technology (PIT) goals, interventions at the graduate level remain largely unexplored.

Towards Robust Data-Driven Control Synthesis for Nonlinear Systems with Actuation Uncertainty

no code implementations21 Nov 2020 Andrew J. Taylor, Victor D. Dorobantu, Sarah Dean, Benjamin Recht, Yisong Yue, Aaron D. Ames

Modern nonlinear control theory seeks to endow systems with properties such as stability and safety, and has been deployed successfully across various domains.

Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions

1 code implementation30 Oct 2020 Sarah Dean, Andrew J. Taylor, Ryan K. Cosner, Benjamin Recht, Aaron D. Ames

The guarantees ensured by these controllers often rely on accurate estimates of the system state for determining control actions.

Certainty Equivalent Perception-Based Control

1 code implementation27 Aug 2020 Sarah Dean, Benjamin Recht

In order to certify performance and safety, feedback control requires precise characterization of sensor errors.

Autonomous Driving regression

Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning

1 code implementation ICML 2020 Esther Rolf, Max Simchowitz, Sarah Dean, Lydia T. Liu, Daniel Björkegren, Moritz Hardt, Joshua Blumenstock

Our theoretical results characterize the optimal strategies in this class, bound the Pareto errors due to inaccuracies in the scores, and show an equivalence between optimal strategies and a rich class of fairness-constrained profit-maximizing policies.

BIG-bench Machine Learning Fairness

Recommendations and User Agency: The Reachability of Collaboratively-Filtered Information

2 code implementations20 Dec 2019 Sarah Dean, Sarah Rich, Benjamin Recht

When the systems are deployed, these models determine the availability of content and information to different users.

Recommendation Systems

Robust Guarantees for Perception-Based Control

no code implementations L4DC 2020 Sarah Dean, Nikolai Matni, Benjamin Recht, Vickie Ye

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 vehicle position, is extracted from complex and nonlinear data, such as a camera image.

Autonomous Vehicles Position

Safely Learning to Control the Constrained Linear Quadratic Regulator

2 code implementations26 Sep 2018 Sarah Dean, Stephen Tu, Nikolai Matni, Benjamin Recht

We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques.

A Broader View on Bias in Automated Decision-Making: Reflecting on Epistemology and Dynamics

no code implementations2 Jul 2018 Roel Dobbe, Sarah Dean, Thomas Gilbert, Nitin Kohli

Machine learning (ML) is increasingly deployed in real world contexts, supplying actionable insights and forming the basis of automated decision-making systems.

BIG-bench Machine Learning Decision Making +2

Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator

no code implementations NeurIPS 2018 Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, Stephen Tu

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs.

Delayed Impact of Fair Machine Learning

3 code implementations ICML 2018 Lydia T. Liu, Sarah Dean, Esther Rolf, Max Simchowitz, Moritz Hardt

Fairness in machine learning has predominantly been studied in static classification settings without concern for how decisions change the underlying population over time.

BIG-bench Machine Learning Fairness

On the Sample Complexity of the Linear Quadratic Regulator

no code implementations4 Oct 2017 Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, Stephen Tu

This paper addresses the optimal control problem known as the Linear Quadratic Regulator in the case when the dynamics are unknown.

Cannot find the paper you are looking for? You can Submit a new open access paper.