Pith. sign in

REVIEW

Searching for Robustness: Loss Learning for Noisy Classification Tasks

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 2103.00243 v1 pith:4AHHS63X submitted 2021-02-27 cs.LG

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

We present a "learning to learn" approach for automatically constructing white-box classification loss functions that are robust to label noise in the training data. We parameterize a flexible family of loss functions using Taylor polynomials, and apply evolutionary strategies to search for noise-robust losses in this space. To learn re-usable loss functions that can apply to new tasks, our fitness function scores their performance in aggregate across a range of training dataset and architecture combinations. The resulting white-box loss provides a simple and fast "plug-and-play" module that enables effective noise-robust learning in diverse downstream tasks, without requiring a special training procedure or network architecture. The efficacy of our method is demonstrated on a variety of datasets with both synthetic and real label noise, where we compare favourably to previous work.

Discussion (0). Continue with ORCID to comment.

Pith tools