mlsanityData to 7 Oct 2026

A Parametric Contextual Online Learning Theory of Brokerage

arXiv 2407.01566 ↗First posted 22 May 2024q-fin.CP cs.GT cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We study the role of contextual information in the online learning problem of brokerage between traders. In this sequential problem, at each time step, two traders arrive with secret valuations about an asset they wish to trade. The learner (a broker) suggests a trading (or brokerage) price based on contextual data about the asset and the market conditions. Then, the traders reveal their willingness to buy or sell based on whether their valuations are higher or lower than the brokerage price. A trade occurs if one of the two traders decides to buy and the other to sell, i.e., if the broker's proposed price falls between the smallest and the largest of their two valuations. We design algorithms for this problem and prove optimal theoretical regret guarantees under various standard assumptions.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 37 of its 65 references that are in the map. First posted on arXiv 22 May 2024.

Builds on

37 of 65 references.

References · 37

  1. 2020Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspectivecited by 78
  2. 2017Efficient Contextual Bandits in Non-stationary Worldscited by 62
  3. 2019Model selection for contextual banditscited by 60
  4. 2016Dynamic Pricing in High-dimensionscited by 55
  5. 2019Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adaptingcited by 42
  6. 2020Efficient and Robust Algorithms for Adversarial Linear Contextual Banditscited by 42
  7. 2013Learning Prices for Repeated Auctions with Strategic Buyerscited by 37
  8. 2020Dynamic Incentive-aware Learning: Robust Pricing in Contextual Auctionscited by 34
  9. 2022Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regressioncited by 30
  10. 2021Bilateral Trade: A Regret Minimization Perspectivecited by 29
  11. 2016Multidimensional Binary Search for Contextual Decision-Makingcited by 27
  12. 2018Contextual Search via Intrinsic Volumescited by 26
25 more
  1. 2019Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimescited by 25
  2. 2021Policy Optimization Using Semi-parametric Models for Dynamic Pricingcited by 23
  3. 2021Logarithmic Regret in Feature-based Dynamic Pricingcited by 22
  4. 2021Distribution-free Contextual Dynamic Pricingcited by 22
  5. 2020Taking a hint: How to leverage loss predictors in contextual bandits?cited by 20
  6. 2021A Regret Analysis of Bilateral Tradecited by 19
  7. 2021Learning to Bid in Contextual First Price Auctionscited by 19
  8. 2022Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithmscited by 19
  9. 2019Stochastic Bandits with Context Distributionscited by 18
  10. 2019Semi-parametric dynamic contextual pricingcited by 17
  11. 2023No-Regret Learning in Bilateral Trade via Global Budget Balancecited by 17
  12. 2023Repeated Bilateral Trade Against a Smoothed Adversarycited by 15
  13. 2023The Role of Transparency in Repeated First-Price Auctions with Unknown Valuationscited by 15
  14. 2020Efficient Two-Sided Markets with Limited Informationcited by 14
  15. 2017Approximating Gains from Trade in Two-sided Markets via Simple Mechanismscited by 11
  16. 2018Contextual bandits with surrogate losses: Margin bounds and efficient algorithmscited by 10
  17. 2021Fixed-Price Approximations in Bilateral Tradecited by 10
  18. 2021Approximately Efficient Bilateral Tradecited by 9
  19. 2017Fixed Price Approximability of the Optimal Gain From Tradecited by 8
  20. 2020A Nearest Neighbor Characterization of Lebesgue Points in Metric Measure Spacescited by 8
  21. 2023An Online Learning Theory of Brokeragecited by 8
  22. 2019Bulow-Klemperer-Style Results for Welfare Maximization in Two-Sided Marketscited by 7
  23. 2016Approximately Efficient Two-Sided Combinatorial Auctionscited by 6
  24. 2022Non-Obvious Manipulability for Single-Parameter Agents and Bilateral Tradecited by 4
  25. 2023Adaptive maximization of social welfarecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Market Making without Regretcited by 4
  2. 2025A Tight Regret Analysis of Non-Parametric Repeated Contextual Brokeragecited by 2
  3. 2026Profit Maximization in Bilateral Trade against a Smooth Adversarycited by 1
  4. 2026Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret without a Variance Boundcited by 0