Learning without the Phase: Regularized PhaseMax Achieves Optimal Sample Complexity
Authors: Fariborz Salehi, Ehsan Abbasi, Babak Hassibi
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The theory well matches empirical results from numerical simulations. Figure 2: Phase transition regimes for the regularized Phase Max problem in terms of the oversampling ratio δ and ρinit = xinit Tx0, for the cases of x0 with (a) no structure and (b) sparse signal recovery . The blue lines indicate the theoretical estimate for the phase transition derived from Theorem 2. The red line in (a) correspond to the upper bound calculated by Theorem 1. In the simulations we used signals of size n = 128. The result is averaged over 10 independent realization of the measurements. |
| Researcher Affiliation | Academia | Fariborz Salehi Department of Electrical Engineering Caltech fsalehi@caltech.edu Ehsan Abbasi Department of Electrical Engineering Caltech eabbasi@caltech.edu Babak Hassibi Department of Electrical Engineering Caltech hassibi@caltech.edu |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement about releasing open-source code for the methodology described. |
| Open Datasets | No | The paper describes the generation of synthetic data for simulations ('ai s are drawn independently from a Gaussian distribution with mean zero and covariance matrix In.') but does not reference any publicly available datasets or provide access information for the data used in simulations. |
| Dataset Splits | No | The paper describes numerical simulations but does not explicitly provide details about training, validation, or test dataset splits. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software names with version numbers used for the experiments. |
| Experiment Setup | Yes | In the simulations we used signals of size n = 128. The result is averaged over 10 independent realization of the measurements. The values of λ in this figure are normalized by ρinit n x0 , which is the maximum acceptable value of λ in the regularized Phase Max. |