跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24881 · v1

Monoculture Robust Learning

单一栽培鲁棒学习

首次提交 2026-11-19 02:27
版本更新 2026-11-19 02:27
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

We introduce a notion of monoculture robustness in Probably Approximately Correct (PAC) learning, as a way to mitigate the problem of algorithmic monoculture (Kleinberg and Raghavan, 2021): the tendency of models sharing the same components (e.g., training data) to fail on the same inputs. Specifically, we ask whether a learner with access to a single dataset can output kk individually accurate hypotheses whose joint failure probability is comparable to training on kk independent datasets. We say that such a learning procedure achieves monoculture robustness, and we quantify this by bounding the conjunctive error that all kk hypotheses misclassify points in an individual sense. We design methods for achieving this type of guarantee by drawing a surprising connection between replicability (Impagliazzo et al., 2022) and monoculture robustness. Specifically, we show that if the base learner is ρρ-replicable, then running it independently kk times on the same sample yields individual monoculture error that shrinks exponentially with kk, controlled by the single-run error of the base learner at the point and ρρ. We complement these positive results with a lower bound: for individual monoculture robustness, we prove a worst-case lower bound showing that, for learners, driving the individual conjunctive error down to γγ can require a sample-size multiplier of t=Ω(log⁡(1/γ))t = Ω(\log(1/γ)).

AI 论文解读

基于摘要 · 非全文审阅

在PAC学习中定义“单一栽培鲁棒性”,并揭示可复制性与该鲁棒性之间的意外联系,使同一数据集上独立训练的k个假设的联合失败概率随k指数下降。

正在读取账号与研究记录…

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 02:27 · 最新观测版本

Monoculture Robust Learning

We introduce a notion of monoculture robustness in Probably Approximately Correct (PAC) learning, as a way to mitigate the problem of algorithmic monoculture (Kleinberg and Raghavan, 2021): the tendency of models sharing the same components (e.g., training data) to fail on the same inputs. Specifically, we ask whether a learner with access to a single dataset can output kk individually accurate hypotheses whose joint failure probability is comparable to training on kk independent datasets. We say that such a learning procedure achieves monoculture robustness, and we quantify this by bounding the conjunctive error that all kk hypotheses misclassify points in an individual sense. We design methods for achieving this type of guarantee by drawing a surprising connection between replicability (Impagliazzo et al., 2022) and monoculture robustness. Specifically, we show that if the base learner is ρρ-replicable, then running it independently kk times on the same sample yields individual monoculture error that shrinks exponentially with kk, controlled by the single-run error of the base learner at the point and ρρ. We complement these positive results with a lower bound: for individual monoculture robustness, we prove a worst-case lower bound showing that, for learners, driving the individual conjunctive error down to γγ can require a sample-size multiplier of t=Ω(log⁡(1/γ))t = Ω(\log(1/γ)).

查看此版本解读 →查看此版本原文 ↗