Can linear algebra create perfect knockoffs?
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912219069939712 |
|---|---|
| author | Hemmens, Christopher Robert-Nicoud, Stephan |
| author_facet | Hemmens, Christopher Robert-Nicoud, Stephan |
| contents | As new Model-X knockoff construction techniques are developed, primarily concerned with determining the correct conditional distribution from which to sample, we focus less on deriving the correct multivariate distribution and instead ask if ``perfect'' knockoffs can be constructed using linear algebra. Using mean absolute correlation between knockoffs and features as a measure of quality, we do produce knockoffs that are pseudo-perfect, however, the optimization algorithm is computationally very expensive. We outline a series of methods to significantly reduce the computation time of the algorithm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02148 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Can linear algebra create perfect knockoffs? Hemmens, Christopher Robert-Nicoud, Stephan Methodology As new Model-X knockoff construction techniques are developed, primarily concerned with determining the correct conditional distribution from which to sample, we focus less on deriving the correct multivariate distribution and instead ask if ``perfect'' knockoffs can be constructed using linear algebra. Using mean absolute correlation between knockoffs and features as a measure of quality, we do produce knockoffs that are pseudo-perfect, however, the optimization algorithm is computationally very expensive. We outline a series of methods to significantly reduce the computation time of the algorithm. |
| title | Can linear algebra create perfect knockoffs? |
| topic | Methodology |
| url | https://arxiv.org/abs/2502.02148 |