On Spectral Learning for Odeco Tensors: Perturbation, Initialization, and Algorithms
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_ | 1866912615272284160 |
|---|---|
| author | Auddy, Arnab Yuan, Ming |
| author_facet | Auddy, Arnab Yuan, Ming |
| contents | We study spectral learning for orthogonally decomposable (odeco) tensors, emphasizing the interplay between statistical limits, optimization geometry, and initialization. Unlike matrices, recovery for odeco tensors does not hinge on eigengaps, yielding improved robustness under noise. While iterative methods such as tensor power iterations can be statistically efficient, initialization emerges as the main computational bottleneck. We investigate perturbation bounds, non-convex optimization analysis, and initialization strategies, clarifying when efficient algorithms attain statistical limits and when fundamental barriers remain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25126 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On Spectral Learning for Odeco Tensors: Perturbation, Initialization, and Algorithms Auddy, Arnab Yuan, Ming Machine Learning Numerical Analysis Statistics Theory We study spectral learning for orthogonally decomposable (odeco) tensors, emphasizing the interplay between statistical limits, optimization geometry, and initialization. Unlike matrices, recovery for odeco tensors does not hinge on eigengaps, yielding improved robustness under noise. While iterative methods such as tensor power iterations can be statistically efficient, initialization emerges as the main computational bottleneck. We investigate perturbation bounds, non-convex optimization analysis, and initialization strategies, clarifying when efficient algorithms attain statistical limits and when fundamental barriers remain. |
| title | On Spectral Learning for Odeco Tensors: Perturbation, Initialization, and Algorithms |
| topic | Machine Learning Numerical Analysis Statistics Theory |
| url | https://arxiv.org/abs/2509.25126 |