Multi-reference alignment in high dimensions: sample complexity and phase transition

by   Elad Romanov, et al.

Multi-reference alignment entails estimating a signal in ℝ^L from its circularly-shifted and noisy copies. This problem has been studied thoroughly in recent years, focusing on the finite-dimensional setting (fixed L). Motivated by single-particle cryo-electron microscopy, we analyze the sample complexity of the problem in the high-dimensional regime L→∞. Our analysis uncovers a phase transition phenomenon governed by the parameter α = L/(σ^2log L), where σ^2 is the variance of the noise. When α>2, the impact of the unknown circular shifts on the sample complexity is minor. Namely, the number of measurements required to achieve a desired accuracy ε approaches σ^2/ε for small ε; this is the sample complexity of estimating a signal in additive white Gaussian noise, which does not involve shifts. In sharp contrast, when α≤ 2, the problem is significantly harder and the sample complexity grows substantially quicker with σ^2.



page 1

page 2

page 3

page 4


Multi-Reference Alignment for sparse signals, Uniform Uncertainty Principles and the Beltway Problem

Motivated by cutting-edge applications like cryo-electron microscopy (cr...

Phase Transition for Support Recovery from Gaussian Linear Measurements

We study the problem of recovering the common k-sized support of a set o...

Rank-one Multi-Reference Factor Analysis

In recent years, there is a growing need for processing methods aimed at...

Sparse multi-reference alignment: sample complexity and computational hardness

Motivated by the problem of determining the atomic structure of macromol...

Empirical or Invariant Risk Minimization? A Sample Complexity Perspective

Recently, invariant risk minimization (IRM) was proposed as a promising ...

Rates of estimation for high-dimensional multi-reference alignment

We study the continuous multi-reference alignment model of estimating a ...

Unbiasing Procedures for Scale-invariant Multi-reference Alignment

This article discusses a generalization of the 1-dimensional multi-refer...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.