Work

Data coarse graining can improve model performance.

Year: 2025

Type: preprint

Abstract: scheme that integrates out more relevant, higher-signal features is purely detrimental. Crucially, using optimal regularization, we demonstrate that this nonmonotonicity is a distinct effect of data coarse graining and not an artifact of double descent. Our framework offers a clear, analytical explanation for why careful data augmentation works: it strips away less relevant degrees of freedom and isolates more predictive signals. Our results highlight a complex, nonmonotonic risk landscape shaped by the structure of the data, and illustrate how ideas from statistical physics provide a principled lens for understanding modern machine learning phenomena.

Source: PubMed

Authors: Alex Nguyen, David J Schwab, Vudtiwat Ngampruetikorn

Institutions: Princeton University, The Graduate Center, CUNY, City University of New York, The University of Sydney

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Institutes of Health

Award: Cloud-based Software Framework to Simplify and Standardize Real-Time fMRI

OpenAlex ID: W4414564517

Cites: 1

Cited by:

Related to: 10