ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2205.01847
22
5

Rates of estimation for high-dimensional multi-reference alignment

4 May 2022
Zehao Dou
Z. Fan
Harrison H. Zhou
ArXivPDFHTML
Abstract

We study the continuous multi-reference alignment model of estimating a periodic function on the circle from noisy and circularly-rotated observations. Motivated by analogous high-dimensional problems that arise in cryo-electron microscopy, we establish minimax rates for estimating generic signals that are explicit in the dimension KKK. In a high-noise regime with noise variance σ2≳K\sigma^2 \gtrsim Kσ2≳K, for signals with Fourier coefficients of roughly uniform magnitude, the rate scales as σ6\sigma^6σ6 and has no further dependence on the dimension. This rate is achieved by a bispectrum inversion procedure, and our analyses provide new stability bounds for bispectrum inversion that may be of independent interest. In a low-noise regime where σ2≲K/log⁡K\sigma^2 \lesssim K/\log Kσ2≲K/logK, the rate scales instead as Kσ2K\sigma^2Kσ2, and we establish this rate by a sharp analysis of the maximum likelihood estimator that marginalizes over latent rotations. A complementary lower bound that interpolates between these two regimes is obtained using Assouad's hypercube lemma. We extend these analyses also to signals whose Fourier coefficients have a slow power law decay.

View on arXiv
Comments on this paper