arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.11571cs.LGcs.CCcs.DS
收藏

AdaBoost 不是一个最优的弱到强学习器

AdaBoost is not an Optimal Weak to Strong Learner

Mikael Møller Høgsgaard, Kasper Green Larsen, Martin Ritzert

AI总结:

本文证明经典 boosting 算法 AdaBoost 及其变体在样本复杂度上并非最优,在强学习器的期望精度上至少差了一个对数因子。

摘要:

AdaBoost 是一种经典的 boosting 算法,用于组合由弱学习器产生的多个不准确的分类器,以在给定足够训练数据时生成具有任意高精度的强学习器。确定获得给定强学习器精度所需的最优样本数,是一个基本的学习理论问题。Larsen 和 Ritzert(NeurIPS'22)最近提出了第一个可证明最优的弱到强学习器。然而,他们的算法有些复杂,原型 boosting 算法 AdaBoost 是否也最优地利用了训练样本仍是一个引人关注的问题。在本工作中,我们对这个问题给出了否定的回答。具体来说,我们证明了 AdaBoost 及其经典变体的样本复杂度,在强学习器的期望精度上至少差了一个对数因子。

英文摘要:

AdaBoost is a classic boosting algorithm for combining multiple inaccurate classifiers produced by a weak learner, to produce a strong learner with arbitrarily high accuracy when given enough training data. Determining the optimal number of samples necessary to obtain a given accuracy of the strong learner, is a basic learning theoretic question. Larsen and Ritzert (NeurIPS'22) recently presented the first provably optimal weak-to-strong learner. However, their algorithm is somewhat complicated and it remains an intriguing question whether the prototypical boosting algorithm AdaBoost also makes optimal use of training samples. In this work, we answer this question in the negative. Concretely, we show that the sample complexity of AdaBoost, and other classic variations thereof, are sub-optimal by at least one logarithmic factor in the desired accuracy of the strong learner.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑