Dynamic Pricing and Learning with Bayesian Persuasion
Dec 10, 2023
Speakers
Shipra Agrawal
Speaker · 0 followers
Yiding Feng
Speaker · 0 followers
About
We consider a novel dynamic pricing and learning setting where in addition to setting prices of products in sequential rounds, the seller also ex-ante commits to ‘advertising schemes’. That is, in the beginning of each round the seller can decide what kind of signal they will provide to the buyer about the product’s quality upon realization. Using the popular Bayesian persuasion framework to model the effect of these signals on the buyers’ valuation and purchase responses, we formulate the problem of finding an optimal design of the advertising scheme along with a pricing scheme that maximizes the seller’s expected revenue. Without any apriori knowledge of the buyers’ demand function, our goal is to design an online algorithm that can use past purchase responses to adaptively learn the optimal pricing and advertising strategy. We study the regret of the algorithm when compared to the optimal clairvoyant price and advertisingscheme. Our main result is a computationally efficient online algorithm that achieves an O(T^2/3(m log T )^1/3) regret bound when the valuation function is linear in the product quality. Here m is the cardinality of the discrete product quality domain and T is the time horizon. This result requires some natural monotonicity and Lipschitz assumptions on the valuation function, but no Lipschitz or smoothness assumption on the buyers’ demand function. For constant m, our result matches the regret lower bound for dynamic pricing within logarithmic factors, which is a special case of our problem. We also obtain several improved results for the widely considered special case of additive valuations, including an Õ(T^2/3) regret bound independent of m when m< T^1/3.We consider a novel dynamic pricing and learning setting where in addition to setting prices of products in sequential rounds, the seller also ex-ante commits to ‘advertising schemes’. That is, in the beginning of each round the seller can decide what kind of signal they will provide to the buyer about the product’s quality upon realization. Using the popular Bayesian persuasion framework to model the effect of these signals on the buyers’ valuation and purchase responses, we formulate the prob…
Organizer
NeurIPS 2023
Account · 645 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
Watch later
Mathieu Even, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Real-time Carbon Footprint Minimization in Sustainable Data Centers wth Reinforcement Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
MeltingTeam Solution for Melting Pot Contest
Watch later
Yunke Ao, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Recent and Upcoming Developments in Randomized Numerical Linear Algebra for ML
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Adversarial Learning for Feature Shift Detection and Correction
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Bicriteria Approximation Algorithms for the Submodular Cover Problem
Watch later
Wenjing Chen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%