Optimal No-regret Learning in Repeated First-price Auctions

03/22/2020
by   Yanjun Han, et al.
0

We study online learning in repeated first-price auctions with censored feedback, where a bidder, only observing the winning bid at the end of each auction, learns to adaptively bid in order to maximize her cumulative payoff. To achieve this goal, the bidder faces a challenging dilemma: if she wins the bid–the only way to achieve positive payoffs–then she is not able to observe the highest bid of the other bidders, which we assume is iid drawn from an unknown distribution. This dilemma, despite being reminiscent of the exploration-exploitation trade-off in contextual bandits, cannot directly be addressed by the existing UCB or Thompson sampling algorithms in that literature, mainly because contrary to the standard bandits setting, when a positive reward is obtained here, nothing about the environment can be learned. In this paper, by exploiting the structural properties of first-price auctions, we develop the first learning algorithm that achieves O(√(T)log^2 T) regret bound when the bidder's private values are stochastically generated. We do so by providing an algorithm on a general class of problems, which we call monotone group contextual bandits, where the same regret bound is established under stochastically generated contexts. Further, by a novel lower bound argument, we characterize an Ω(T^2/3) lower bound for the case where the contexts are adversarially generated, thus highlighting the impact of the contexts generation mechanism on the fundamental learning limit. Despite this, we further exploit the structure of first-price auctions and develop a learning algorithm that operates sample-efficiently (and computationally efficiently) in the presence of adversarially generated private values. We establish an O(√(T)log^5 T) regret bound for this algorithm, hence providing a complete characterization of optimal learning guarantees for this problem.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/25/2018

Contextual Bandits with Cross-learning

In the classical contextual bandits problem, in each round t, a learner ...
research
11/14/2019

Online Second Price Auction with Semi-bandit Feedback Under the Non-Stationary Setting

In this paper, we study the non-stationary online second price auction p...
research
09/26/2013

Finite-Time Analysis of Kernelised Contextual Bandits

We tackle the problem of online reward maximisation over a large finite ...
research
04/14/2020

Sequential Batch Learning in Finite-Action Linear Contextual Bandits

We study the sequential batch learning problem in linear contextual band...
research
06/06/2020

Contextual Bandits with Side-Observations

We investigate contextual bandits in the presence of side-observations a...
research
01/12/2023

Statistical Learning with Sublinear Regret of Propagator Models

We consider a class of learning problems in which an agent liquidates a ...
research
07/09/2020

Learning to Bid Optimally and Efficiently in Adversarial First-price Auctions

First-price auctions have very recently swept the online advertising ind...

Please sign up or login with your details

Forgot password? Click here to reset