arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2009.12583cs.LGstat.ML
收藏

小数据,大决策:小数据体系中的模型选择

Small Data, Big Decisions: Model Selection in the Small-Data Regime

DeepMind(深度思维)

Jorg Bornschein, Francesco Visin, Simon Osindero

摘要:

高度过参数化的神经网络可以表现出令人好奇的强大泛化性能--为了更好地理解这一现象,最近已经积累了大量的理论和实证研究。与大多数以前的工作相反,这些工作通常认为性能是模型大小的函数,在本文中,我们经验性地研究了当训练集的大小在多个数量级上变化时的泛化性能。这些系统性的实验产生了一些有趣且可能非常有用的观察结果;也许最值得注意的是,在较小的数据子集上进行训练可以导致更可靠的模型选择决策,同时享受更小的计算成本。此外,我们的实验使我们能够估计最小描述LQs的常见数据集给定现代神经网络架构,从而铺平了道路的原则模型选择考虑到奥卡姆剃刀。

英文摘要:

Highly overparametrized neural networks can display curiously strong generalization performance - a phenomenon that has recently garnered a wealth of theoretical and empirical research in order to better understand it. In contrast to most previous work, which typically considers the performance as a function of the model size, in this paper we empirically study the generalization performance as the size of the training set varies over multiple orders of magnitude. These systematic experiments lead to some interesting and potentially very useful observations; perhaps most notably that training on smaller subsets of the data can lead to more reliable model selection decisions whilst simultaneously enjoying smaller computational costs. Our experiments furthermore allow us to estimate Minimum Description Lengths for common datasets given modern neural network architectures, thereby paving the way for principled model selection taking into account Occams-razor.

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。

↑