mlsanityData to 7 Oct 2026

Learning from Streaming Data when Users Choose

arXiv 2406.01481 ↗First posted 3 Jun 2024cs.LG cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

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. The service providers' models influence which service the user will choose at the next time step, and the user's choice, in return, influences the model update, leading to a feedback loop. In this paper, we formalize the above dynamics and develop a simple and efficient decentralized algorithm to locally minimize the overall user loss. Theoretically, we show that our algorithm asymptotically converges to stationary points of of the overall loss almost surely. We also experimentally demonstrate the utility of our algorithm with real world data.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 30 of its 57 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

30 of 57 references.

References · 30

  1. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  2. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  3. 2020Performative Predictioncited by 318
  4. 2019Momentum-Based Variance Reduction in Non-Convex SGDcited by 302
  5. 2015Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decompositioncited by 241
  6. 2018On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizescited by 155
  7. 2020Online stochastic gradient descent on non-convex losses from high-dimensional inferencecited by 119
  8. 2015Characterizing Concept Driftcited by 93
  9. 2022Multiplayer Performative Prediction: Learning in Decision-Dependent Gamescited by 42
  10. 2021One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profilescited by 39
  11. 2019Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairnesscited by 38
  12. 2022Multi-agent Performative Prediction: From Global Stability and Optimality to Chaoscited by 33
18 more
  1. 2022Multi-agent Performative Prediction with Greedy Deployment and Consensus Seeking Agentscited by 23
  2. 2021Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learningcited by 20
  3. 2021Online Projected Gradient Descent for Stochastic Optimization with Decision-Dependent Distributionscited by 17
  4. 2022Competition, Alignment, and Equilibria in Digital Marketplacescited by 17
  5. 2019Regression Equilibriumcited by 16
  6. 2023Improved Bayes Risk Can Yield Reduced Social Welfare Under Competitioncited by 14
  7. 2019Online k-means Clusteringcited by 13
  8. 2020Distributed Stochastic Gradient Descent: Nonconvexity, Nonsmoothness, and Convergence to Local Minimacited by 13
  9. 2014An Algorithm for Online K-Means Clusteringcited by 12
  10. 2016Convergence rate of stochastic k-meanscited by 8
  11. 2017Stochastic Nonconvex Optimization with Large Minibatchescited by 7
  12. 2018Distributed Stochastic Optimization via Adaptive SGDcited by 7
  13. 2022Competition over data: how does data purchase affect users?cited by 5
  14. 2022Emergent specialization from participation dynamics and multi-learner retrainingcited by 5
  15. 2020Asymptotic Analysis of Conditioned Stochastic Gradient Descentcited by 4
  16. 2022Convergence of online k-meanscited by 4
  17. 2024Strategic Usage in a Multi-Learner Settingcited by 3
  18. 2021Leveraging User Behavior History for Personalized Email Searchcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2025A Market for Accuracy: Classification under Competitioncited by 6
  2. 2024Safety vs. Performance: How Multi-Objective Learning Reduces Barriers to Market Entrycited by 4