Pith. sign in

REVIEW 4 cited by

Early Stopping without a Validation Set

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1703.09580 v3 pith:COUPWM5B submitted 2017-03-28 cs.LG stat.ML

Maren Mahsereci , Lukas Balles , Christoph Lassner , Philipp Hennig This is my paper · ORCID
classification cs.LGstat.ML
keywords earlystoppingvalidationgeneralizationperformancetrainingapproachcommon
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Early stopping is a widely used technique to prevent poor generalization performance when training an over-expressive model by means of gradient-based optimization. To find a good point to halt the optimizer, a common practice is to split the dataset into a training and a smaller validation set to obtain an ongoing estimate of the generalization performance. We propose a novel early stopping criterion based on fast-to-compute local statistics of the computed gradients and entirely removes the need for a held-out validation set. Our experiments show that this is a viable approach in the setting of least-squares and logistic regression, as well as neural networks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. ScoreStop: Gradient-based early stopping using functional score tests

    stat.ML 2026-06 unverdicted novelty 7.0 of 10

    ScoreStop introduces a functional score test for early stopping in gradient boosting, testing the null that the current predictor minimizes population risk with a scale-invariant statistic of known asymptotic distribution.

  2. Early Stopping Against Label Noise Without Validation Data

    cs.LG 2025-02 conditional novelty 6.0 of 10

    The first local minimum of prediction changes on the noisy training set selects a near-optimal early stopping point without any validation data.

  3. Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set

    cs.CL 2019-09 conditional novelty 5.0 of 10

    Using a development set for early stopping can change reported accuracy for low-resource NLP models, with per-language differences up to 18 percentage points compared to tuning training length on other languages.

  4. AutoML: A Survey of the State-of-the-Art

    cs.LG 2019-08 unverdicted novelty 1.0 of 10

    A survey that organizes AutoML into a four-stage pipeline and reviews neural architecture search methods, their performance, and open problems.

Pith tools