MétaCan
Menu
Back to cohort
Record W4416393741 · doi:10.1016/j.ifacol.2025.11.051

On strict verification of neural Lyapunov functions

2025· article· en· W4416393741 on OpenAlexaff
Jun Liu, Maxwell Fitzsimmons

Bibliographic record

VenueIFAC-PapersOnLine · 2025
Typearticle
Languageen
FieldPhysics and Astronomy
TopicModel Reduction and Neural Networks
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsLyapunov functionArtificial neural networkLyapunov redesignControl theory (sociology)Lyapunov equationEquilibrium pointLyapunov optimizationFeedforward neural network

Abstract

fetched live from OpenAlex

Determination of Lyapunov functions has been one of the most fundamental challenges in the analysis and control of nonlinear systems. There has been significant recent interest in using neural networks to compute Lyapunov functions. Often, the loss function is modified to encourage the Lyapunov conditions, and the architecture of the neural network is also adapted to satisfy certain Lyapunov conditions by design. However, it remains unclear whether all conditions can be strictly verified and whether such modifications are necessary. In this paper, we investigate this question. We show that, under the usual assumption that the equilibrium point is exponentially stable, a standard feedforward neural network trained using the usual Lyapunov conditions can be easily modified after training to become strictly verifiable. We demonstrate the results with numerical examples.

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.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.008
metaresearch head score (Gemma)0.066
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.008
Threshold uncertainty score0.044

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0080.066
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0010.004
Scholarly communication0.0020.004
Open science0.0020.003
Research integrity0.0020.004
Insufficient payload (model declined to judge)0.0040.001

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 head0.009
GPT teacher head0.261
Teacher spread0.252 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueIFAC-PapersOnLineSame topicModel Reduction and Neural NetworksFrench-language works237,207