Pith. sign in

REVIEW 1 cited by

Revisiting Checkpoint Averaging for Neural Machine Translation

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 2210.11803 v1 pith:MEI7DRMF submitted 2022-10-21 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords averagingcheckpointtranslationmachineneuralsimplecheckpointsconverged
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models. The calculation is cheap to perform and the fact that the translation improvement almost comes for free, makes it widely adopted in neural machine translation research. Despite the popularity, the method itself simply takes the mean of the model parameters from several checkpoints, the selection of which is mostly based on empirical recipes without many justifications. In this work, we revisit the concept of checkpoint averaging and consider several extensions. Specifically, we experiment with ideas such as using different checkpoint selection strategies, calculating weighted average instead of simple mean, making use of gradient information and fine-tuning the interpolation weights on development data. Our results confirm the necessity of applying checkpoint averaging for optimal performance, but also suggest that the landscape between the converged checkpoints is rather flat and not much further improvement compared to simple averaging is to be obtained.

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. FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition

    cs.LG 2025-05 conditional novelty 5.0 of 10

    FCOS combines channel clustering and layer collapse diagnosis to prune AMR models by over 95% with minimal accuracy loss.

Pith tools