MétaCan
Menu
Back to cohort
Record W4416978430 · doi:10.1038/s41467-025-66983-3

Sufficient is better than optimal for training neural networks

2025· article· en· W4416978430 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueNature Communications · 2025
Typearticle
Languageen
FieldComputer Science
TopicStochastic Gradient Optimization Techniques
Canadian institutionsQueen's University
FundersNatural Sciences and Engineering Research Council of CanadaGovernment of CanadaUniversities Space Research Association
KeywordsOverfittingLeverage (statistics)Spurious relationshipArtificial neural networkDeep neural networksConvolutional neural networkFeedforward neural networkTraining (meteorology)

Abstract

fetched live from OpenAlex

The array of neural network training techniques that invoke optimization but rely on ad hoc modification for validity suggests that optimization-based training is misguided. Shortcomings of optimization-based training are brought to strong relief by overfitting, where naive optimization produces spurious outcomes. Here, we introduce simmering, a physics-based method that trains neural networks to generate “good enough” weights and biases, paradoxically outperforming leading optimization-based approaches. Instead of optimizing, simmering systematically samples non-optimal weights and biases to generate an ensemble that provides sufficient representations of the underlying phenomenon. Simmering corrects neural networks that are overfit by optimization, and produces more generalizable predictions if deployed from the outset compared to other overfitting mitigation methods. Our results question optimization as a paradigm for training transformers, and feedforward and convolutional neural networks. We leverage information-geometric arguments to point to the existence of classes of sufficient-training algorithms that do not take optimization as their starting point. The authors propose simmering, a physics-inspired alternative to optimization-based neural network training that generates weights through systematic sampling rather than optimization, to mitigate overfitting and achieve better generalization compared to conventional methods.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.974
Threshold uncertainty score0.524

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0030.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.031
GPT teacher head0.316
Teacher spread0.285 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it