Sample completion, structured correlation, and Netflix problems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911174173392896 |
|---|---|
| author | Coregliano, Leonardo N. Malliaris, Maryanthe |
| author_facet | Coregliano, Leonardo N. Malliaris, Maryanthe |
| contents | We develop a new high-dimensional statistical learning model which can take advantage of structured correlation in data even in the presence of randomness. We completely characterize learnability in this model in terms of VCN${}_{k,k}$-dimension (essentially $k$-dependence from Shelah's classification theory). This model suggests a theoretical explanation for the success of certain algorithms in the 2006~Netflix Prize competition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20404 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sample completion, structured correlation, and Netflix problems Coregliano, Leonardo N. Malliaris, Maryanthe Machine Learning Logic Statistics Theory Primary: 68Q32. Secondary: 68T05, 60F15 We develop a new high-dimensional statistical learning model which can take advantage of structured correlation in data even in the presence of randomness. We completely characterize learnability in this model in terms of VCN${}_{k,k}$-dimension (essentially $k$-dependence from Shelah's classification theory). This model suggests a theoretical explanation for the success of certain algorithms in the 2006~Netflix Prize competition. |
| title | Sample completion, structured correlation, and Netflix problems |
| topic | Machine Learning Logic Statistics Theory Primary: 68Q32. Secondary: 68T05, 60F15 |
| url | https://arxiv.org/abs/2509.20404 |