Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.18274 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914814838702080 |
|---|---|
| author | Moniri, Behrad Hassani, Hamed |
| author_facet | Moniri, Behrad Hassani, Hamed |
| contents | In this paper, we study a nonlinear spiked random matrix model where a nonlinear function is applied element-wise to a noise matrix perturbed by a rank-one signal. We establish a signal-plus-noise decomposition for this model and identify precise phase transitions in the structure of the signal components at critical thresholds of signal strength. To demonstrate the applicability of this decomposition, we then utilize it to study new phenomena in the problems of signed signal recovery in nonlinear models and community detection in transformed stochastic block models. Finally, we validate our results through a series of numerical simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_18274 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models Moniri, Behrad Hassani, Hamed Statistics Theory Machine Learning Signal Processing In this paper, we study a nonlinear spiked random matrix model where a nonlinear function is applied element-wise to a noise matrix perturbed by a rank-one signal. We establish a signal-plus-noise decomposition for this model and identify precise phase transitions in the structure of the signal components at critical thresholds of signal strength. To demonstrate the applicability of this decomposition, we then utilize it to study new phenomena in the problems of signed signal recovery in nonlinear models and community detection in transformed stochastic block models. Finally, we validate our results through a series of numerical simulations. |
| title | Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models |
| topic | Statistics Theory Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2405.18274 |