✳flâneur — a map of the web's best reading

[2110.03922] The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks

arxiv.org · 17,713 words · saved by 1 readers

Abstract:We derive simple closed-form estimates for the test risk and other generalization metrics of kernel ridge regression (KRR). Relative to prior work, our derivations are greatly simplified and our final expressions are more readily interpreted. These improvements are enabled by our identification of a sharp conservation law which limits the ability of KRR to learn any orthonormal basis of functions. Test risk and other objects of interest are expressed transparently in terms of our conserved quantity evaluated in the kernel eigenbasis. We use our improved framework to: i) provide a theoretical explanation for the "deep bootstrap" of Nakkiran et al (2020), ii) generalize a previous result regarding the hardness of the classic parity problem, iii) fashion a theoretical tool for the study of adversarial robustness, and iv) draw a tight analogy between KRR and a well-studied system in statistical physics.

# link_z3r1zz18z1.pdf ## Metadata - PDFFormatVersion=1.5 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - CreationDate=D:20231030010754Z - Creator=LaTeX with hyperref - ModDate=D:20231030010754Z - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) kpathsea version 6.3.5 - Producer=pdfTeX-1.40.25 - Trapped=False ## Contents ### Page 1 The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural NetworksJames B. Simon james.simon@berkeley.edu Uni

Explore this link on the map →

saved by

related reading