Abstract
We study the performance of Empirical Risk Minimization in both noisy and noiseless phase retrieval problems, indexed by subsets of $\mathbb{R}^n$ and relative to subgaussian sampling; that is, when the given data is $y_i=\left a_i,x_0\right^2+w_i$ for a subgaussian random vector $a$, independent noise $w$ and a fixed but unknown $x_0$ that belongs to a given subset of $\mathbb{R}^n$.
We show that ERM produces $\hat{x}$ whose Euclidean distance to either $x_0$ or $-x_0$ depends on the gaussian mean-width of the indexing set and on the signal-to-noise ratio of the problem. The bound coincides with the one for linear regression when $\|x_0\|_2$ is of the order of a constant. In addition, we obtain a minimax lower bound for the problem and identify sets for which ERM is a minimax procedure. As examples, we study the class of $d$-sparse vectors in $\mathbb{R}^n$ and the unit ball in $\ell_1^n$.
Citation
Guillaume Lecué. Shahar Mendelson. "Minimax rate of convergence and the performance of empirical risk minimization in phase recovery." Electron. J. Probab. 20 1 - 29, 2015. https://doi.org/10.1214/EJP.v20-3525
Information