跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.25757 · v1

Uniqueness, Proximity, and Scaling in Atomic Splittable Polymatroid Congestion Games

首次提交 2026-11-19 17:00
版本更新 2026-11-19 17:00
雷达观测 2026-11-20 19:58
arXiv ↗PDF ↗

摘要

We give a polynomial-time algorithm for exact equilibrium computation in atomic splittable polymatroid congestion games with integral ranks and rational player-specific affine latencies with positive slopes. The algorithm first computes equilibria of associated integer-splittable games, in which demands are allocated in multiples of a common packet size. For arbitrary polymatroid bases, no polynomial-time algorithm for these discrete equilibria was previously known. We provide such an algorithm and use progressively finer packets to recover the continuous equilibrium exactly. Our proof uses the multiple-exchange theorem of Oki and Schwarcz (2025) to obtain two exchange matchings that yield equilibrium proximity under changes of packet sizes and ranks, independently of cost coefficients. We then bound the matching deficiency caused by rank changes and construct compatible submodular rank roundings. Together these give a polynomial-time packet-halving algorithm using polynomially many submodular-function minimizations and exact rational arithmetic. The analysis rests on a uniqueness theorem of independent interest: for arbitrary real polymatroid ranks and continuously differentiable, strictly increasing, convex latencies, we prove uniqueness of equilibria, resolving a previously open problem.

作者备注:41 pages

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 17:00 · 最新观测版本

Uniqueness, Proximity, and Scaling in Atomic Splittable Polymatroid Congestion Games

We give a polynomial-time algorithm for exact equilibrium computation in atomic splittable polymatroid congestion games with integral ranks and rational player-specific affine latencies with positive slopes. The algorithm first computes equilibria of associated integer-splittable games, in which demands are allocated in multiples of a common packet size. For arbitrary polymatroid bases, no polynomial-time algorithm for these discrete equilibria was previously known. We provide such an algorithm and use progressively finer packets to recover the continuous equilibrium exactly. Our proof uses the multiple-exchange theorem of Oki and Schwarcz (2025) to obtain two exchange matchings that yield equilibrium proximity under changes of packet sizes and ranks, independently of cost coefficients. We then bound the matching deficiency caused by rank changes and construct compatible submodular rank roundings. Together these give a polynomial-time packet-halving algorithm using polynomially many submodular-function minimizations and exact rational arithmetic. The analysis rests on a uniqueness theorem of independent interest: for arbitrary real polymatroid ranks and continuously differentiable, strictly increasing, convex latencies, we prove uniqueness of equilibria, resolving a previously open problem.

查看此版本解读 →查看此版本原文 ↗