Optimal Spectral Algorithms for Correlated Two-view Models in High Dimensions
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916025689178112 |
|---|---|
| author | Du, Hang Hu, Henry Lepsveridze, Saba |
| author_facet | Du, Hang Hu, Henry Lepsveridze, Saba |
| contents | We study high-dimensional inference in correlated two-view models, focusing on spectral methods for strong detection and weak recovery. We introduce a general framework, motivated by a TAP type heuristic from statistical physics, that provides a unified treatment of three canonical models: high-dimensional canonical correlation analysis, and the correlated spiked Wigner and Wishart models. Our main contribution is to construct explicit spectral algorithms in all three settings, that achieve strong detection and weak recovery down to the corresponding thresholds, where we prove matching information-theoretic lower bounds. Furthermore, our spectral procedures operate without knowledge of the model parameters, relying solely on the observed data. This demonstrates the optimality of spectral methods in these models and the broad statistical applicability of the framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_19364 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Optimal Spectral Algorithms for Correlated Two-view Models in High Dimensions Du, Hang Hu, Henry Lepsveridze, Saba Statistics Theory Probability 60B20, 62B10, 62H15, 62H12, 62H25 We study high-dimensional inference in correlated two-view models, focusing on spectral methods for strong detection and weak recovery. We introduce a general framework, motivated by a TAP type heuristic from statistical physics, that provides a unified treatment of three canonical models: high-dimensional canonical correlation analysis, and the correlated spiked Wigner and Wishart models. Our main contribution is to construct explicit spectral algorithms in all three settings, that achieve strong detection and weak recovery down to the corresponding thresholds, where we prove matching information-theoretic lower bounds. Furthermore, our spectral procedures operate without knowledge of the model parameters, relying solely on the observed data. This demonstrates the optimality of spectral methods in these models and the broad statistical applicability of the framework. |
| title | Optimal Spectral Algorithms for Correlated Two-view Models in High Dimensions |
| topic | Statistics Theory Probability 60B20, 62B10, 62H15, 62H12, 62H25 |
| url | https://arxiv.org/abs/2605.19364 |