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 2303.00564stat.MLcond-mat.dis-nncs.LG
收藏

深度结构化高斯特征模型的学习曲线

Learning curves for deep structured Gaussian feature models

Harvard University(哈佛大学)

Jacob A. Zavatone-Veth, Cengiz Pehlevan

AI总结:

本文利用统计物理的副本技巧推导了多层结构化高斯特征模型的学习曲线,发现第一层特征行间相关性有助于泛化,而后续层的结构通常有害,揭示了权重结构对泛化的影响。

摘要:

近年来,深度学习理论界广泛关注分析模型何时能在插值训练数据的同时,依然对未见样本具有良好的泛化能力。通过研究多层高斯随机特征模型,人们已获得许多深刻见解,该模型能够计算出精确的泛化渐近性。然而,很少有工作考虑权重各向异性的影响;大多数研究假设随机特征由独立同分布的高斯权重生成,且仅允许输入数据中存在结构。在此,我们利用统计物理中的副本技巧(replica trick),推导了具有多层结构化高斯特征模型的学习曲线。我们证明,允许第一层特征行之间的相关性有助于提升泛化能力,而后续层中的结构通常是有害的。我们的结果揭示了在一类简单的可解模型中,权重结构如何影响泛化能力。

英文摘要:

In recent years, significant attention in deep learning theory has been devoted to analyzing when models that interpolate their training data can still generalize well to unseen examples. Many insights have been gained from studying models with multiple layers of Gaussian random features, for which one can compute precise generalization asymptotics. However, few works have considered the effect of weight anisotropy; most assume that the random features are generated using independent and identically distributed Gaussian weights, and allow only for structure in the input data. Here, we use the replica trick from statistical physics to derive learning curves for models with many layers of structured Gaussian features. We show that allowing correlations between the rows of the first layer of features can aid generalization, while structure in later layers is generally detrimental. Our results shed light on how weight structure affects generalization in a simple class of solvable models.

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。

↑