Search Results for author:
Found 31 papers, 16 papers with code
Learning Linear Dynamics from Bilinear Observations
We consider the problem of learning a realization of a partially observed dynamical system with linear state transitions and bilinear observations.
Harm Mitigation in Recommender Systems under User Preference Dynamics
We consider a recommender system that takes into account the interplay between recommendations, the evolution of user interests, and harmful content.
Random Features Approximation for Control-Affine Systems
Modern data-driven control applications call for flexible nonlinear models that are amenable to principled controller synthesis and realtime feedback.
Learning from Streaming Data when Users Choose
In digital markets comprised of many competing services, each user chooses between multiple service providers according to their preferences, and the chosen service makes use of the user data to incrementally improve its model.
Accounting for AI and Users Shaping One Another: The Role of Mathematical Models
As AI systems enter into a growing number of societal domains, these systems increasingly shape and are shaped by user preferences, opinions, and behaviors.
Strategic Usage in a Multi-Learner Setting
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
(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
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.
Decision-aid or Controller? Steering Human Decision Makers with Algorithms
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
Datasets for training recommender systems are often subject to distribution shift induced by users' and recommenders' selection biases.
Perception-Based Sampled-Data Optimization of Dynamical Systems
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.
Online Convex Optimization with Unbounded Memory
As a special case, we prove the first non-trivial lower bound for OCO with finite memory \citep{anavaHM2015online}, which could be of independent interest, and also improve existing upper bounds.
Modeling Content Creator Incentives on Algorithm-Curated Platforms
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 specialization from participation dynamics and multi-learner retraining
Numerous online services are data-driven: the behavior of users affects the system's parameters, and the system's parameters affect the users' experience of the service, which in turn affects the way users may interact with the system.
Preference Dynamics Under Personalized Recommendations
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
Building systems that are good for society in the face of complex societal effects requires a dynamic approach.
Choices, Risks, and Reward Reports: Charting Public Policy for Reinforcement Learning Systems
In the long term, reinforcement learning (RL) is considered by many AI theorists to be the most promising path to artificial general intelligence.
Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability
In this work, we consider how preference models in interactive recommendation systems determine the availability of content and users' opportunities for discovery.
AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks
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
Modern nonlinear control theory seeks to endow systems with properties such as stability and safety, and has been deployed successfully across various domains.
Do Offline Metrics Predict Online Performance in Recommender Systems?
We observe that offline metrics are correlated with online performance over a range of environments.
Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions
The guarantees ensured by these controllers often rely on accurate estimates of the system state for determining control actions.
Certainty Equivalent Perception-Based Control
In order to certify performance and safety, feedback control requires precise characterization of sensor errors.
Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning
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.
Recommendations and User Agency: The Reachability of Collaboratively-Filtered Information
When the systems are deployed, these models determine the availability of content and information to different users.
Robust Guarantees for Perception-Based Control
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.
Safely Learning to Control the Constrained Linear Quadratic Regulator
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
Machine learning (ML) is increasingly deployed in real world contexts, supplying actionable insights and forming the basis of automated decision-making systems.
Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator
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
Fairness in machine learning has predominantly been studied in static classification settings without concern for how decisions change the underlying population over time.
On the Sample Complexity of the Linear Quadratic Regulator
This paper addresses the optimal control problem known as the Linear Quadratic Regulator in the case when the dynamics are unknown.
