Misspecified Nonconvex Statistical Optimization for Phase Retrieval
arXiv:1712.06245
Abstract
Existing nonconvex statistical optimization theory and methods crucially rely on the correct specification of the underlying "true" statistical models. To address this issue, we take a first step towards taming model misspecification by studying the high-dimensional sparse phase retrieval problem with misspecified link functions. In particular, we propose a simple variant of the thresholded Wirtinger flow algorithm that, given a proper initialization, linearly converges to an estimator with optimal statistical accuracy for a broad family of unknown link functions. We further provide extensive numerical experiments to support our theoretical findings.
56 pages
References in corpus (12)
- The LASSO with Non-linear Measurements is Equivalent to One With Linear Measurements
- High-dimensional estimation with geometric constraints
- Sparse single-index model
- Convergence rate bounds for a proximal ADMM with over-relaxation stepsize parameter for solving nonconvex linearly constrained problems
- Sparse Nonlinear Regression: Parameter Estimation and Asymptotic Inference
- Optimal linear estimation under unknown nonlinear transform
- Sparse PCA with Oracle Property
- On consistency and sparsity for sliced inverse regression in high dimensions
- Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes
- Structured signal recovery from non-linear and heavy-tailed measurements
- Sparse Generalized Eigenvalue Problem: Optimal Statistical Rates via Truncated Rayleigh Flow
- On Quadratic Convergence of DC Proximal Newton Algorithm for Nonconvex Sparse Learning in High Dimensions