Bispectrum Inversion With Application to Multireference Alignment
From MaRDI portal
Abstract: We consider the problem of estimating a signal from noisy circularly-translated versions of itself, called multireference alignment (MRA). One natural approach to MRA could be to estimate the shifts of the observations first, and infer the signal by aligning and averaging the data. In contrast, we consider a method based on estimating the signal directly, using features of the signal that are invariant under translations. Specifically, we estimate the power spectrum and the bispectrum of the signal from the observations. Under mild assumptions, these invariant features contain enough information to infer the signal. In particular, the bispectrum can be used to estimate the Fourier phases. To this end, we propose and analyze a few algorithms. Our main methods consist of non-convex optimization over the smooth manifold of phases. Empirically, in the absence of noise, these non-convex algorithms appear to converge to the target signal with random initialization. The algorithms are also robust to noise. We then suggest three additional methods. These methods are based on frequency marching, semidefinite relaxation and integer programming. The first two methods provably recover the phases exactly in the absence of noise. In the high noise level regime, the invariant features approach for MRA results in stable estimation if the number of measurements scales like the cube of the noise variance, which is the information-theoretic rate. Additionally, it requires only one pass over the data which is important at low signal-to-noise ratio when the number of observations must be large.
Cited in
(31)- Spectral methods from tensor networks
- Deep neural-network prior for orbit recovery from method of moments
- On signal reconstruction from FROG measurements
- Multi-target detection with application to cryo-electron microscopy
- Towards a bilipschitz invariant theory
- Maximum likelihood for high-noise group orbit estimation and single-particle cryo-EM
- The sample complexity of multireference alignment
- Estimation under group actions: recovering orbits from invariants
- Orbit recovery for band-limited functions
- Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model
- Rank-one multi-reference factor analysis
- Power spectrum unbiasing for dilation-invariant multi-reference alignment
- Multi-reference alignment in high dimensions: sample complexity and phase transition
- Method of moments for 3D single particle \textit{ab initio} modeling with non-uniform distribution of viewing angles
- Bearing estimation in the bispectrum domain
- Compactification of the rigid motions group in image processing
- Sparse multi-reference alignment: phase retrieval, uniform uncertainty principles and the beltway problem
- Rates of estimation for high-dimensional multireference alignment
- The stability of generalized phase retrieval problem over compact groups
- The reflection-invariant bispectrum: signal recovery in the dihedral model
- Optimized response function estimation for spherical deconvolution
- Signal recovery from a few linear measurements of its high-order spectra
- The beltway problem over orthogonal groups
- Average-case complexity of tensor decomposition for low-degree polynomials
- Phase retrieval with semialgebraic and ReLU neural network priors
- Likelihood Maximization and Moment Matching in Low <scp>SNR</scp> Gaussian Mixture Models
- Separating polynomial invariants over non-closed fields of finite abelian groups
- A unified approach to synchronization problems over subgroups of the orthogonal group
- Multi-target detection with rotations
- Iterative algorithm for discrete structure recovery
- Benchmark problems for phase retrieval
This page was built for publication: Bispectrum Inversion With Application to Multireference Alignment
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4621616)
