Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space

arXiv:2310.13572v3 Announce Type: replace
Abstract: Double descent presents a counter-intuitive aspect within the machine learning domain, and researchers have observed its manifestation in various models and tasks. While some theoretical explanations have been proposed for this phenomenon in specific contexts, an accepted theory to account for its occurrence in deep learning remains yet to be established. In this study, we revisit the phenomenon of double descent and demonstrate that its occurrence is strongly influenced by the presence of noisy data. …

abstract analysis arxiv counter cs.lg domain feature lens machine machine learning researchers space tasks theory through type while