Minimax Optimality of Classical Scaling Under General Noise Conditions
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909473048625152 |
|---|---|
| author | Vishwanath, Siddharth Arias-Castro, Ery |
| author_facet | Vishwanath, Siddharth Arias-Castro, Ery |
| contents | We establish the consistency of classical scaling under a broad class of noise models, encompassing many commonly studied cases in literature. Our approach requires only finite fourth moments of the noise, significantly weakening standard assumptions. We derive convergence rates for classical scaling and establish matching minimax lower bounds, demonstrating that classical scaling achieves minimax optimality in recovering the true configuration even when the input dissimilarities are corrupted by noise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00947 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Minimax Optimality of Classical Scaling Under General Noise Conditions Vishwanath, Siddharth Arias-Castro, Ery Statistics Theory Machine Learning 62R07, 94A16, 62G05, 62C20 We establish the consistency of classical scaling under a broad class of noise models, encompassing many commonly studied cases in literature. Our approach requires only finite fourth moments of the noise, significantly weakening standard assumptions. We derive convergence rates for classical scaling and establish matching minimax lower bounds, demonstrating that classical scaling achieves minimax optimality in recovering the true configuration even when the input dissimilarities are corrupted by noise. |
| title | Minimax Optimality of Classical Scaling Under General Noise Conditions |
| topic | Statistics Theory Machine Learning 62R07, 94A16, 62G05, 62C20 |
| url | https://arxiv.org/abs/2502.00947 |