mlsanityData to 14 Oct 2026

Doubly Fair Dynamic Pricing

arXiv 2209.11837 ↗First posted 23 Sep 2022cs.LG econ.EM stat.MLcited by 8

Not on the map. Why?

Abstract (arXiv)

We study the problem of online dynamic pricing with two types of fairness constraints: a "procedural fairness" which requires the proposed prices to be equal in expectation among different groups, and a "substantive fairness" which requires the accepted prices to be equal in expectation among different groups. A policy that is simultaneously procedural and substantive fair is referred to as "doubly fair". We show that a doubly fair policy must be random to have higher revenue than the best trivial policy that assigns the same price to different groups. In a two-group setting, we propose an online learning algorithm for the 2-group pricing problems that achieves tildeO(√T) regret, zero procedural unfairness and tildeO(√T) substantive unfairness over T rounds of learning. We also prove two lower bounds showing that these results on regret and unfairness are both information-theoretically optimal up to iterated logarithmic factors. To the best of our knowledge, this is the first dynamic pricing algorithm that learns to price while satisfying two fairness constraints at the same time.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 23 of its 52 references that are in the map. First posted on arXiv 23 Sep 2022.

Builds on

23 of 52 references.

References · 23

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2018A Reductions Approach to Fair Classificationcited by 587
  3. 2020Fairness in Machine Learningcited by 194
  4. 2016Fairness in Learning: Classic and Contextual Banditscited by 168
  5. 2017Online Convex Optimization with Stochastic Constraintscited by 95
  6. 2013Online Learning with Switching Costs and Other Adaptive Adversariescited by 61
  7. 2016Dynamic Pricing in High-dimensionscited by 55
  8. 2020Private Reinforcement Learning with PAC and Regret Guaranteescited by 51
  9. 2018Individual Fairness in Hindsightcited by 33
  10. 2021Decision Making with Differential Privacy under a Fairness Lenscited by 32
  11. 2022Sample-Efficient Reinforcement Learning with loglog(T) Switching Costcited by 32
  12. 2020Metric-Free Individual Fairness in Online Learningcited by 30
11 more
  1. 2018Contextual Search via Intrinsic Volumescited by 26
  2. 2021Policy Optimization Using Semi-parametric Models for Dynamic Pricingcited by 23
  3. 2021Differentially Private Regret Minimization in Episodic Markov Decision Processescited by 23
  4. 2020Local Differential Privacy for Regret Minimization in Reinforcement Learningcited by 22
  5. 2021Logarithmic Regret in Feature-based Dynamic Pricingcited by 22
  6. 2022Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noisecited by 21
  7. 2022Offline Reinforcement Learning with Differential Privacycited by 20
  8. 2022Provably Confidential Language Modellingcited by 13
  9. 2022Differentially Private Linear Sketches: Efficient Implementations and Applicationscited by 10
  10. 2018Reinforcement Learning for Fair Dynamic Pricingcited by 9
  11. 2021Fairness-aware Online Price Discrimination with Nonparametric Demand Modelscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 2; 2025: 2; 2026: 1.

8 papers.

  1. 2022Near-Optimal Differentially Private Reinforcement Learningcited by 16
  2. 2024Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizescited by 12
  3. 2023Pricing with Contextual Elasticity and Heteroscedastic Valuationcited by 5
  4. 2023Utility Fairness in Contextual Dynamic Pricing with Demand Learningcited by 4
  5. 2024Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraintscited by 4
  6. 2025Online Pricing and Allocation with Demand Learning and Fulfillment Costcited by 4
  7. 2025Dynamic Pricing with Adversarially-Censored Demandscited by 4
  8. 2026Optimal Contextual Pricing under Agnostic Non-Lipschitz Demandcited by 2