Pooling, double descent and classical emergence

Blind Review

No cgwq6, OSF Preprints from Center for Open Science

Abstract: In statistics, multiple data points are often pooled together such that it is as if they come from identical random variables - one example of heavy pooling is a fixed effects model. As the number of data pooled successfully increases, the law of large numbers kicks in as to eliminate stochastic variations in the sample average of pooled data. This eliminates stochastic variations such that a model effectively becomes deterministic, with N data points aggregated into one data point. In the big-data regime then, the bias-variance tradeoff becomes largely meaningless - more the model complexity, better the performance. The example of how classical mechanics emerges from quantum mechanics demonstrates such a breakdown.

Date: 2023-10-18
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://osf.io/download/652f54b5164d3207f2a5dced/

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:osf:osfxxx:cgwq6

DOI: 10.31219/osf.io/cgwq6

Access Statistics for this paper

More papers in OSF Preprints from Center for Open Science
Bibliographic data for series maintained by OSF ().