To refer to this page use:
|Abstract:||Multireference alignment (MRA) is the problem of estimating a signal from many noisy and cyclically shifted copies of itself. In this paper, we consider an extension called heterogeneous MRA, where K signals must be estimated, and each observation comes from one of those signals, unknown to us. This is a simplified model for the heterogeneity problem notably arising in cryo-electron microscopy. We propose an algorithm which estimates theK signals without estimating either the shifts or the classes of the observations. It requires only one pass over the data and is based on low-order moments that are invariant under cyclic shifts. Given sufficiently many measurements, one can estimate these invariant features averaged over the K signals. We then design a smooth, non-convex optimization problem to compute a set of signals which are consistent with the estimated averaged features. We find that, in many cases, the proposed approach estimates the set of signals accurately despite non-convexity, and conjecture the number of signals K that can be resolved as a function of the signal length L is on the order of root L.|
|Electronic Publication Date:||24-May-2018|
|Citation:||Boumal, Nicolas, Bendory, Tamir, Lederman, Roy R, Singer, Amit. (2018). HETEROGENEOUS MULTIREFERENCE ALIGNMENT: A SINGLE PASS APPROACH. 2018 52ND ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS (CISS)|
|Type of Material:||Conference Article|
|Journal/Proceeding Title:||2018 52ND ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS (CISS)|
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.