Pith. sign in

REVIEW 1 cited by

Harmless interpolation of noisy data in regression

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1903.09139 v2 pith:YPLBHM24 submitted 2019-03-21 cs.LG stat.ML

classification cs.LGstat.ML
keywords noisedataerrorinterpolatingtrainingfeaturesgeneralizationharmless
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A continuing mystery in understanding the empirical success of deep neural networks is their ability to achieve zero training error and generalize well, even when the training data is noisy and there are more parameters than data points. We investigate this overparameterized regime in linear regression, where all solutions that minimize training error interpolate the data, including noise. We characterize the fundamental generalization (mean-squared) error of any interpolating solution in the presence of noise, and show that this error decays to zero with the number of features. Thus, overparameterization can be explicitly beneficial in ensuring harmless interpolation of noise. We discuss two root causes for poor generalization that are complementary in nature -- signal "bleeding" into a large number of alias features, and overfitting of noise by parsimonious feature selectors. For the sparse linear model with noise, we provide a hybrid interpolating scheme that mitigates both these issues and achieves order-optimal MSE over all possible interpolating solutions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects

    cs.LG 2026-03 conditional novelty 6.0 of 10

    Multi-task learning of related perceptrons is asymptotically a single-task problem plus explicit regularizers that improve generalization and postpone double descent.

Pith tools