Phase retrieval in high dimensions: Statistical and computational phase transitions
We consider the phase retrieval problem of reconstructing a n-dimensional real or complex signal π^β from m (possibly noisy) observations Y_ΞΌ = | β_i=1^n Ξ¦_ΞΌ i X^β_i/β(n)|, for a large class of correlated real and complex random sensing matrices Ξ¦, in a high-dimensional setting where m,nββ while Ξ± = m/n=Ξ(1). First, we derive sharp asymptotics for the lowest possible estimation error achievable statistically and we unveil the existence of sharp phase transitions for the weak- and full-recovery thresholds as a function of the singular values of the matrix Ξ¦. This is achieved by providing a rigorous proof of a result first obtained by the replica method from statistical mechanics. In particular, the information-theoretic transition to perfect recovery for full-rank matrices appears at Ξ±=1 (real case) and Ξ±=2 (complex case). Secondly, we analyze the performance of the best-known polynomial time algorithm for this problem β approximate message-passing β establishing the existence of a statistical-to-algorithmic gap depending, again, on the spectral properties of Ξ¦. Our work provides an extensive classification of the statistical and algorithmic thresholds in high-dimensional phase retrieval for a broad class of random matrices.
READ FULL TEXT