mlsanityData to 14 Oct 2026

Dynamic pricing and assortment under a contextual MNL demand

arXiv 2110.10018 ↗First posted 19 Oct 2021cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

We consider dynamic multi-product pricing and assortment problems under an unknown demand over T periods, where in each period, the seller decides on the price for each product or the assortment of products to offer to a customer who chooses according to an unknown Multinomial Logit Model (MNL). Such problems arise in many applications, including online retail and advertising. We propose a randomized dynamic pricing policy based on a variant of the Online Newton Step algorithm (ONS) that achieves a O(d√Tlog(T)) regret guarantee under an adversarial arrival model. We also present a new optimistic algorithm for the adversarial MNL contextual bandits problem, which achieves a better dependency than the state-of-the-art algorithms in a problem-dependent constant kappa2 (potentially exponentially small). Our regret upper bound scales as tildeO(d√kappa2 T+ log(T)/kappa2), which gives a stronger bound than the existing tildeO(d√T/kappa2) guarantees.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 16 of its 48 references that are in the map. First posted on arXiv 19 Oct 2021.

Builds on

16 of 48 references.

References · 16

  1. 2020Improved Optimistic Algorithms for Logistic Banditscited by 118
  2. 2020Instance-Wise Minimax-Optimal Algorithms for Logistic Banditscited by 57
  3. 2016Dynamic Pricing in High-dimensionscited by 55
  4. 2017MNL-Bandit: A Dynamic Learning Approach to Assortment Selectioncited by 50
  5. 2017Provably Optimal Algorithms for Generalized Linear Contextual Banditscited by 38
  6. 2017Thompson Sampling for the MNL-Banditcited by 35
  7. 2016Dynamic Pricing with Demand Covariatescited by 31
  8. 2018Dynamic Assortment Optimization with Changing Contextual Informationcited by 28
  9. 2016Multidimensional Binary Search for Contextual Decision-Makingcited by 27
  10. 2015Online Stochastic Linear Optimization under One-bit Feedbackcited by 26
  11. 2018Contextual Search via Intrinsic Volumescited by 26
  12. 2021Logarithmic Regret in Feature-based Dynamic Pricingcited by 22
4 more
  1. 2021Multinomial Logit Contextual Bandits: Provable Optimality and Practicalitycited by 21
  2. 2017Perishability of Data: Dynamic Pricing under Varying-Coefficient Modelscited by 19
  3. 2015Composite convex minimization involving self-concordant-like cost functionscited by 12
  4. 2019Multi-Product Dynamic Pricing in High-Dimensions with Heterogeneous Price Sensitivitycited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 6; 2025: 7; 2026: 5.

20 papers.

Sort:

By area:

  1. 2024Nearly Minimax Optimal Regret for Multinomial Logistic Banditcited by 20
  2. 2025Improved Online Confidence Bounds for Multinomial Logistic Banditscited by 15
  3. 2022Model-Based Reinforcement Learning with Multinomial Logistic Function Approximationcited by 13
  4. 2024Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximationcited by 10
  5. 2024Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximationcited by 7
  6. 2024Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transitioncited by 6
  7. 2023Pricing with Contextual Elasticity and Heteroscedastic Valuationcited by 5
  8. 2024Contextual Multinomial Logit Bandits with General Value Functionscited by 4
  9. 2025Learning an Optimal Assortment Policy under Observational Datacited by 4
  10. 2025Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal Algorithmcited by 3
  11. 2024Low-Rank Online Dynamic Assortment with Dual Contextual Informationcited by 2
  12. 2025Dynamic Assortment Selection and Pricing with Censored Preference Feedbackcited by 2
8 more
  1. 2025Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Optionscited by 2
  2. 2025On Pareto Optimality for Parametric Choice Banditscited by 0
  3. 2025Stochastic Matching Bandits with Rare Optimization Updatescited by 0
  4. 2026Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilitiescited by 0
  5. 2026Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPscited by 0
  6. 2026Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identificationcited by 0
  7. 2026Diversified Multinomial Logit Contextual Banditscited by 0
  8. 2026Learning Choice Model Trees for Feature-Based Multi-Product Pricing: Exact Optimization and Field Evidencecited by 0