Pith. sign in

REVIEW

Leveraging Local Variation in Data: Sampling and Weighting Schemes for Supervised Deep Learning

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 2101.07561 v3 pith:VFSHKEUC submitted 2021-01-19 stat.ML cs.LGmath.STstat.TH

Leveraging Local Variation in Data: Sampling and Weighting Schemes for Supervised Deep Learning

classification stat.ML cs.LGmath.STstat.TH
keywords neuraldatafunctiondistributionlearnlearninglocalmethodology
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In the context of supervised learning of a function by a neural network, we claim and empirically verify that the neural network yields better results when the distribution of the data set focuses on regions where the function to learn is steep. We first traduce this assumption in a mathematically workable way using Taylor expansion and emphasize a new training distribution based on the derivatives of the function to learn. Then, theoretical derivations allow constructing a methodology that we call Variance Based Samples Weighting (VBSW). VBSW uses labels local variance to weight the training points. This methodology is general, scalable, cost-effective, and significantly increases the performances of a large class of neural networks for various classification and regression tasks on image, text, and multivariate data. We highlight its benefits with experiments involving neural networks from linear models to ResNet and Bert.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.