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 2406.02663stat.MLcond-mat.dis-nncs.LG
收藏

揭秘真实世界数据上的谱偏置

Demystifying Spectral Bias on Real-World Data

Racah Institute of Physics(拉卡物理研究所);Hebrew University of Jerusalem(耶路撒冷希伯来大学)

Itay Lavie, Zohar Ringel

AI总结:

针对真实数据上核特征值问题难以求解的问题,本文提出利用理想化数据测度的特征值与特征函数分析跨数据集可学习性,从而揭示复杂数据集上的谱偏置并给出可学习性界。

摘要:

核岭回归(KRR)和高斯过程(GP)是统计学与机器学习中的基础工具,近期还被应用于高度过参数化的深度神经网络。这些工具学习目标函数的能力,与其在输入数据分布上采样得到的核的特征值直接相关。支撑在较高特征值上的目标更具可学习性。然而,在真实世界数据上求解此类特征值问题仍是一项挑战。本文研究跨数据集可学习性,并表明可以利用与高度理想化数据测度相关的特征值和特征函数,揭示复杂数据集上的谱偏置,并界定真实世界数据上的可学习性。这使我们能够利用现实核所表现出的各种对称性,来阐明其谱偏置。

英文摘要:

Kernel ridge regression (KRR) and Gaussian processes (GPs) are fundamental tools in statistics and machine learning, with recent applications to highly over-parameterized deep neural networks. The ability of these tools to learn a target function is directly related to the eigenvalues of their kernel sampled on the input data distribution. Targets that have support on higher eigenvalues are more learnable. However, solving such eigenvalue problems on real-world data remains a challenge. Here, we consider cross-dataset learnability and show that one may use eigenvalues and eigenfunctions associated with highly idealized data measures to reveal spectral bias on complex datasets and bound learnability on real-world data. This allows us to leverage various symmetries that realistic kernels manifest to unravel their spectral bias.

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。

↑