MétaCan
Menu
Back to cohort
Record W4366390417 · doi:10.3390/make5020024

Lottery Ticket Search on Untrained Models with Applied Lottery Sample Selection

2023· article· en· W4366390417 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

VenueMachine Learning and Knowledge Extraction · 2023
Typearticle
Languageen
FieldPsychology
TopicGambling Behavior and Treatments
Canadian institutionsUniversity of Windsor
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsLotteryComputer scienceTicketFraction (chemistry)Machine learningSample (material)Set (abstract data type)Selection (genetic algorithm)Artificial intelligenceArtificial neural networkProcess (computing)MathematicsStatisticsComputer security

Abstract

fetched live from OpenAlex

In this paper, we present a new approach to improve tabular datasets by applying the lottery ticket hypothesis to tabular neural networks. Prior approaches were required to train the original large-sized model to find these lottery tickets. In this paper we eliminate the need to train the original model and discover lottery tickets using networks a fraction of the model’s size. Moreover, we show that we can remove up to 95% of the training dataset to discover lottery tickets, while still maintaining similar accuracy. The approach uses a genetic algorithm (GA) to train candidate pruned models by encoding the nodes of the original model for selection measured by performance and weight metrics. We found that the search process does not require a large portion of the training data, but when the final pruned model is selected it can be retrained on the full dataset, even if it is often not required. We propose a lottery sample hypothesis similar to the lottery ticket hypotheses where a subsample of lottery samples of the training set can train a model with equivalent performance to the original dataset. We show that the combination of finding lottery samples alongside lottery tickets can allow for faster searches and greater accuracy.

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: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.519
Threshold uncertainty score0.912

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.001

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 head0.085
GPT teacher head0.390
Teacher spread0.305 · 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