No-Regret Learning in Partially-Informed Auctions

by   Wenshuo Guo, et al.

Auctions with partially-revealed information about items are broadly employed in real-world applications, but the underlying mechanisms have limited theoretical support. In this work, we study a machine learning formulation of these types of mechanisms, presenting algorithms that are no-regret from the buyer's perspective. Specifically, a buyer who wishes to maximize his utility interacts repeatedly with a platform over a series of T rounds. In each round, a new item is drawn from an unknown distribution and the platform publishes a price together with incomplete, "masked" information about the item. The buyer then decides whether to purchase the item. We formalize this problem as an online learning task where the goal is to have low regret with respect to a myopic oracle that has perfect knowledge of the distribution over items and the seller's masking function. When the distribution over items is known to the buyer and the mask is a SimHash function mapping ℝ^d to {0,1}^ℓ, our algorithm has regret 𝒪̃((Tdℓ)^1/2). In a fully agnostic setting when the mask is an arbitrary function mapping to a set of size n, our algorithm has regret 𝒪̃(T^3/4n^1/2). Finally, when the prices are stochastic, the algorithm has regret 𝒪̃((Tn)^1/2).


page 1

page 2

page 3

page 4


Regret in Online Recommendation Systems

This paper proposes a theoretical analysis of recommendation systems in ...

Logarithmic regret in the dynamic and stochastic knapsack problem

We study a dynamic and stochastic knapsack problem in which a decision m...

Cascading Bandits for Large-Scale Recommendation Problems

Most recommender systems recommend a list of items. The user examines th...

Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty

In online marketplaces, customers have access to hundreds of reviews for...

Fast Rate Learning in Stochastic First Price Bidding

First-price auctions have largely replaced traditional bidding approache...

Online Learning to Rank with Features

We introduce a new model for online ranking in which the click probabili...

Multinomial Logit Bandit with Linear Utility Functions

Multinomial logit bandit is a sequential subset selection problem which ...

Please sign up or login with your details

Forgot password? Click here to reset