Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.04282 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929700976197632 |
|---|---|
| author | Straziota, Davide Saglietti, Luca |
| author_facet | Straziota, Davide Saglietti, Luca |
| contents | Real-valued Phase retrieval is a non-convex continuous inference problem, where a high-dimensional signal is to be reconstructed from a dataset of signless linear measurements. Focusing on the noiseless case, we aim to disentangle the two distinct sub-tasks entailed in the Phase retrieval problem: the hard combinatorial problem of retrieving the missing signs of the measurements, and the nested convex problem of regressing the input-output observations to recover the hidden signal. To this end, we introduce and analytically characterize a two-level formulation of the problem, called ``Phase selection''. Within the Replica Theory framework, we perform a large deviation analysis to characterize the minimum mean squared error achievable with different guesses for the hidden signs. Moreover, we study the free-energy landscape of the problem when both levels are optimized simultaneously, as a function of the dataset size. At low temperatures, in proximity to the Bayes-optimal threshold -- previously derived in the context of Phase retrieval -- we detect the coexistence of two free-energy branches, one connected to the random initialization condition and a second to the signal. We derive the phase diagram for a first-order transition after which the two branches merge. Interestingly, introducing an $L_2$ regularization in the regression sub-task can anticipate the transition to lower dataset sizes, at the cost of a bias in the signal reconstructions which can be removed by annealing the regularization intensity. Finally, we study the inference performance of three meta-heuristics in the context of Phase selection: Simulated Annealing, Approximate Message Passing, and Langevin Dynamics on the continuous relaxation of the sign variables. With simultaneous annealing of the temperature and the $L_2$ regularization, they are shown to approach the Bayes-optimal sample efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_04282 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Isolating the hard core of phaseless inference: the Phase selection formulation Straziota, Davide Saglietti, Luca Disordered Systems and Neural Networks Real-valued Phase retrieval is a non-convex continuous inference problem, where a high-dimensional signal is to be reconstructed from a dataset of signless linear measurements. Focusing on the noiseless case, we aim to disentangle the two distinct sub-tasks entailed in the Phase retrieval problem: the hard combinatorial problem of retrieving the missing signs of the measurements, and the nested convex problem of regressing the input-output observations to recover the hidden signal. To this end, we introduce and analytically characterize a two-level formulation of the problem, called ``Phase selection''. Within the Replica Theory framework, we perform a large deviation analysis to characterize the minimum mean squared error achievable with different guesses for the hidden signs. Moreover, we study the free-energy landscape of the problem when both levels are optimized simultaneously, as a function of the dataset size. At low temperatures, in proximity to the Bayes-optimal threshold -- previously derived in the context of Phase retrieval -- we detect the coexistence of two free-energy branches, one connected to the random initialization condition and a second to the signal. We derive the phase diagram for a first-order transition after which the two branches merge. Interestingly, introducing an $L_2$ regularization in the regression sub-task can anticipate the transition to lower dataset sizes, at the cost of a bias in the signal reconstructions which can be removed by annealing the regularization intensity. Finally, we study the inference performance of three meta-heuristics in the context of Phase selection: Simulated Annealing, Approximate Message Passing, and Langevin Dynamics on the continuous relaxation of the sign variables. With simultaneous annealing of the temperature and the $L_2$ regularization, they are shown to approach the Bayes-optimal sample efficiency. |
| title | Isolating the hard core of phaseless inference: the Phase selection formulation |
| topic | Disordered Systems and Neural Networks |
| url | https://arxiv.org/abs/2502.04282 |