Saved in:
Bibliographic Details
Main Author: Zhao, Hangyi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.06851
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915842044723200
author Zhao, Hangyi
author_facet Zhao, Hangyi
contents We study contextual bilateral trade under full feedback when trader valuations have bounded density but infinite variance. We first extend the self-bounding property of Bachoc et al. (ICML 2025) from bounded to real-valued valuations, showing that the expected regret of any price $π$ satisfies $\mathbb{E}[g(m,V,W) - g(π,V,W)] \le L|m-π|^2$ under bounded density alone. Combining this with truncated-mean estimation, we prove that an epoch-based algorithm achieves regret $\widetilde{O}(T^{1-2β(p-1)/(βp + d(p-1))})$ when the noise has finite $p$-th moment for $p \in (1,2)$ and the market value function is $β$-Hölder, and we establish a matching $Ω(\cdot)$ lower bound via Assouad's method with a smoothed moment-matching construction. Our results characterize the exact minimax rate for this problem, interpolating between the classical nonparametric rate at $p=2$ and the trivial linear rate as $p \to 1^+$.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06851
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret with Infinite Variance
Zhao, Hangyi
Machine Learning
Computer Science and Game Theory
We study contextual bilateral trade under full feedback when trader valuations have bounded density but infinite variance. We first extend the self-bounding property of Bachoc et al. (ICML 2025) from bounded to real-valued valuations, showing that the expected regret of any price $π$ satisfies $\mathbb{E}[g(m,V,W) - g(π,V,W)] \le L|m-π|^2$ under bounded density alone. Combining this with truncated-mean estimation, we prove that an epoch-based algorithm achieves regret $\widetilde{O}(T^{1-2β(p-1)/(βp + d(p-1))})$ when the noise has finite $p$-th moment for $p \in (1,2)$ and the market value function is $β$-Hölder, and we establish a matching $Ω(\cdot)$ lower bound via Assouad's method with a smoothed moment-matching construction. Our results characterize the exact minimax rate for this problem, interpolating between the classical nonparametric rate at $p=2$ and the trivial linear rate as $p \to 1^+$.
title Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret with Infinite Variance
topic Machine Learning
Computer Science and Game Theory
url https://arxiv.org/abs/2603.06851