arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.08483cs.LGstat.ML
收藏

关于深系综中的幂律

On Power Laws in Deep Ensembles

National Research University Higher School of Economics(国家研究型高等经济大学);Samsung AI Center(三星人工智能中心)

Ekaterina Lobacheva, Nadezhda Chirkova, Maxim Kodryan, Dmitry Vetrov

摘要:

众所周知,深度神经网络的集合在不确定性估计中实现了最先进的性能,并导致精度提高。在这项工作中,我们专注于一个分类问题,并调查的行为的非校准和校准的负对数似然(CNLL)的深度合奏作为合奏大小和成员网络大小的函数。我们指出的条件下,CNLL遵循幂律w.r.t.系综大小或成员网络大小,并分析所发现的幂律的参数的动态。我们重要的实际发现是,一个大型网络的性能可能比具有相同参数总数的几个中型网络的集合更差(我们称之为记忆分裂)。使用检测到的类似幂律的依赖关系,我们可以预测(1)具有给定结构的网络集成的可能增益,(2)基于相对少量的训练网络,给定内存预算的最佳内存分配。我们在arXiv:2005.07292中更详细地描述了内存分割优势效应

英文摘要:

Ensembles of deep neural networks are known to achieve state-of-the-art performance in uncertainty estimation and lead to accuracy improvement. In this work, we focus on a classification problem and investigate the behavior of both non-calibrated and calibrated negative log-likelihood (CNLL) of a deep ensemble as a function of the ensemble size and the member network size. We indicate the conditions under which CNLL follows a power law w.r.t. ensemble size or member network size, and analyze the dynamics of the parameters of the discovered power laws. Our important practical finding is that one large network may perform worse than an ensemble of several medium-size networks with the same total number of parameters (we call this ensemble a memory split). Using the detected power law-like dependencies, we can predict (1) the possible gain from the ensembling of networks with given structure, (2) the optimal memory split given a memory budget, based on a relatively small number of trained networks. We describe the memory split advantage effect in more details in arXiv:2005.07292

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。

↑