Quantum Implementation of Quadratic Programming for Feature Selection
Bibliographic record
Abstract
This work explores the quantum implementation of Quadratic Programming for Feature Selection (QPFS), a method designed to address the challenges of high-dimensional datasets in machine learning. Feature selection plays a critical role in improving model performance, reducing computational complexity, and mitigating overfitting. QPFS formulates feature selection as a quadratic optimization problem that balances feature relevance and redundancy. We investigate the scalability challenges of QPFS and apply the Nystrom approximation to reduce computational cost. To demonstrate the feasibility of quantum acceleration, the QPFS algorithm was implemented on QCI’s Dirac-3 quantum platform, which leverages high-dimensional qudits for solving optimization problems. Experiments were conducted on the Taiwanese Bankruptcy Prediction dataset, with alternative datasets identified for future exploration. The results highlight key differences between classical and quantum implementations: while the classical solver produced rank-based weights for features, the Dirac-3 quantum solver effectively suppressed redundant and irrelevant features by assigning them near-zero values. This property is significant in simplifying feature selection without additional manual thresholding. The project provides insights into the integration of quantum optimization methods with machine learning pipelines, showing promising directions for scalable feature selection in finance, healthcare, and other high-dimensional domains. The full implementation, including both classical and quantum code, is available on GitHub: https://github.com/Hope-Alemayehu/QPFS-using-Dirac3.
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 | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 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".