Lottery Ticket Search on Untrained Models with Applied Lottery Sample Selection
Bibliographic record
Abstract
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".