Saved in:
Bibliographic Details
Main Authors: Kang, Bosun, Park, Hyejun, Fan, Chenglin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.07313
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911307196792832
author Kang, Bosun
Park, Hyejun
Fan, Chenglin
author_facet Kang, Bosun
Park, Hyejun
Fan, Chenglin
contents We revisit the classic ski rental problem through the lens of Bayesian decision-making and machine-learned predictions. While traditional algorithms minimize worst-case cost without assumptions, and recent learning-augmented approaches leverage noisy forecasts with robustness guarantees, our work unifies these perspectives. We propose a discrete Bayesian framework that maintains exact posterior distributions over the time horizon, enabling principled uncertainty quantification and seamless incorporation of expert priors. Our algorithm achieves prior-dependent competitive guarantees and gracefully interpolates between worst-case and fully-informed settings. Our extensive experimental evaluation demonstrates superior empirical performance across diverse scenarios, achieving near-optimal results under accurate priors while maintaining robust worst-case guarantees. This framework naturally extends to incorporate multiple predictions, non-uniform priors, and contextual information, highlighting the practical advantages of Bayesian reasoning in online decision problems with imperfect predictions.
format Preprint
id arxiv_https___arxiv_org_abs_2512_07313
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning-Augmented Ski Rental with Discrete Distributions: A Bayesian Approach
Kang, Bosun
Park, Hyejun
Fan, Chenglin
Machine Learning
Data Structures and Algorithms
We revisit the classic ski rental problem through the lens of Bayesian decision-making and machine-learned predictions. While traditional algorithms minimize worst-case cost without assumptions, and recent learning-augmented approaches leverage noisy forecasts with robustness guarantees, our work unifies these perspectives. We propose a discrete Bayesian framework that maintains exact posterior distributions over the time horizon, enabling principled uncertainty quantification and seamless incorporation of expert priors. Our algorithm achieves prior-dependent competitive guarantees and gracefully interpolates between worst-case and fully-informed settings. Our extensive experimental evaluation demonstrates superior empirical performance across diverse scenarios, achieving near-optimal results under accurate priors while maintaining robust worst-case guarantees. This framework naturally extends to incorporate multiple predictions, non-uniform priors, and contextual information, highlighting the practical advantages of Bayesian reasoning in online decision problems with imperfect predictions.
title Learning-Augmented Ski Rental with Discrete Distributions: A Bayesian Approach
topic Machine Learning
Data Structures and Algorithms
url https://arxiv.org/abs/2512.07313