两层多数投票提升可复现增强学习的样本效率

Improved Replicable Boosting with Majority-of-Majorities

• 底层用改进的可复现增强算法，顶层再做一次多数投票
• 相比以往方法，样本复杂度显著降低
• 适合关注高效训练和结果可复现的研究者

我们提出一种新的可复现增强算法，相较于先前方法在样本复杂度上有显著提升。该算法通过两层多数投票实现：底层采用Impagliazzo等人[2022]提出的改进型可复现增强算法，顶层再进行一次多数投票，从而增强鲁棒性与效率。

原文摘要 · Abstract (English)

We introduce a new replicable boosting algorithm which significantly improves the sample complexity compared to previous algorithms. The algorithm works by doing two layers of majority voting, using an improved version of the replicable boosting algorithm introduced by Impagliazzo et al. [2022] in the bottom layer.

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。