Online Bidding for Contextual First-Price Auctions with Budgets under One-Sided Information Feedback

TL;DR

This paper introduces a novel online bidding algorithm for first-price auctions with budgets and one-sided feedback, effectively learning contextual bids and achieving near-optimal regret bounds.

Contribution

It proposes a robust regression-based learning method for contextual bids and a dual update algorithm, extending to multi-dimensional settings with demonstrated practical efficiency.

Findings

Achieves ((( ilde{O}(\u0000(( ext{T})))) regret

Develops a novel robust regression method based on conditional quantile invariance

Extends the approach to multi-dimensional auction settings

Abstract

In this paper, we study the problem of learning to bid in repeated first-price auctions with budget constraints. In each period, the decision maker needs to submit a bid to win the auction and maximize the total collected reward, subject to a budget constraint throughout the horizon. We focus on the setting with one-sided information feedback where only the winning bid is revealed to the decision maker at each period. Different from previous papers that assume homogeneous competitors' bids, we assume that the highest bid of other bidders depends on the context of the impression, which is initially unknown and needs to be learned over time. To tackle the learning difficulty, we propose a novel robust regression method based on conditional quantile invariance to learn the contextual parameter. Further combined with a dual update procedure, we develop a new bidding algorithm and prove that our algorithm achieves $\widetilde{O}(\sqrt{T})$ regret, which is order-optimal. We further extend our approach to the multi-dimensional setting and demonstrate the practical efficiency of our algorithm through numerical experiments.