Adaptive Discretization against an Adversary: Lipschitz bandits, Dynamic Pricing, and Auction Tuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Podimata, Chara, Slivkins, Aleksandrs
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918055775305728
author Podimata, Chara
Slivkins, Aleksandrs
author_facet Podimata, Chara
Slivkins, Aleksandrs
contents Lipschitz bandits is a prominent version of multi-armed bandits that studies large, structured action spaces such as the $[0,1]$ interval, where similar actions are guaranteed to have similar rewards. A central theme here is the adaptive discretization of the action space, which gradually ``zooms in'' on the more promising regions thereof. The goal is to take advantage of ``nicer'' problem instances, while retaining near-optimal worst-case performance. While the stochastic version of the problem is well-understood, the general version with adversarial rewards is not. We provide the first algorithm (\emph{Adversarial Zooming}) for adaptive discretization in the adversarial version, and derive instance-dependent regret bounds. In particular, we recover the worst-case optimal regret bound for the adversarial version, and the instance-dependent regret bound for the stochastic version. We apply our algorithm to several fundamental applications -- including dynamic pricing and auction reserve tuning -- all under adversarial reward models. While these domains often violate Lipschitzness, our analysis only requires a weaker version thereof, allowing for meaningful regret bounds without additional smoothness assumptions. Notably, we extend our results to multi-product dynamic pricing with non-smooth reward structures, a setting which does not even satisfy one-sided Lipschitzness.
format Preprint
id arxiv_https___arxiv_org_abs_2006_12367
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Adaptive Discretization against an Adversary: Lipschitz bandits, Dynamic Pricing, and Auction Tuning
Podimata, Chara
Slivkins, Aleksandrs
Machine Learning
Data Structures and Algorithms
Computer Science and Game Theory
Lipschitz bandits is a prominent version of multi-armed bandits that studies large, structured action spaces such as the $[0,1]$ interval, where similar actions are guaranteed to have similar rewards. A central theme here is the adaptive discretization of the action space, which gradually ``zooms in'' on the more promising regions thereof. The goal is to take advantage of ``nicer'' problem instances, while retaining near-optimal worst-case performance. While the stochastic version of the problem is well-understood, the general version with adversarial rewards is not. We provide the first algorithm (\emph{Adversarial Zooming}) for adaptive discretization in the adversarial version, and derive instance-dependent regret bounds. In particular, we recover the worst-case optimal regret bound for the adversarial version, and the instance-dependent regret bound for the stochastic version. We apply our algorithm to several fundamental applications -- including dynamic pricing and auction reserve tuning -- all under adversarial reward models. While these domains often violate Lipschitzness, our analysis only requires a weaker version thereof, allowing for meaningful regret bounds without additional smoothness assumptions. Notably, we extend our results to multi-product dynamic pricing with non-smooth reward structures, a setting which does not even satisfy one-sided Lipschitzness.
title Adaptive Discretization against an Adversary: Lipschitz bandits, Dynamic Pricing, and Auction Tuning
topic Machine Learning
Data Structures and Algorithms
Computer Science and Game Theory
url https://arxiv.org/abs/2006.12367