Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model

03/31/2020
by   Zhou Fan, et al.
0

We study the non-convex optimization landscape for maximum likelihood estimation in the discrete orbit recovery model with Gaussian noise. This model is motivated by applications in molecular microscopy and image processing, where each measurement of an unknown object is subject to an independent random rotation from a rotational group. Equivalently, it is a Gaussian mixture model where the mixture centers belong to a group orbit. We show that fundamental properties of the likelihood landscape depend on the signal-to-noise ratio and the group structure. At low noise, this landscape is "benign" for any discrete group, possessing no spurious local optima and only strict saddle points. At high noise, this landscape may develop spurious local optima, depending on the specific group. We discuss several positive and negative examples, and provide a general condition that ensures a globally benign landscape. For cyclic permutations of coordinates on ℝ^d (multi-reference alignment), there may be spurious local optima when d ≥ 6, and we establish a correspondence between these local optima and those of a surrogate function of the phase variables in the Fourier domain. We show that the Fisher information matrix transitions from resembling that of a single Gaussian in low noise to having a graded eigenvalue structure in high noise, which is determined by the graded algebra of invariant polynomials under the group action. In a local neighborhood of the true object, the likelihood landscape is strongly convex in a reparametrized system of variables given by a transcendence basis of this polynomial algebra. We discuss implications for optimization algorithms, including slow convergence of expectation-maximization, and possible advantages of momentum-based acceleration and variable reparametrization for first- and second-order descent methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/28/2019

Learning rates for Gaussian mixtures under group invariance

We study the pointwise maximum likelihood estimation rates for a class o...
research
07/02/2021

Maximum likelihood for high-noise group orbit estimation and single-particle cryo-EM

Motivated by applications to single-particle cryo-electron microscopy (c...
research
06/26/2020

Likelihood Maximization and Moment Matching in Low SNR Gaussian Mixture Models

We derive an asymptotic expansion for the log likelihood of Gaussian mix...
research
09/28/2020

Likelihood Landscape and Local Minima Structures of Gaussian Mixture Models

In this paper, we study the landscape of the population negative log-lik...
research
08/18/2016

A Tight Convex Upper Bound on the Likelihood of a Finite Mixture

The likelihood function of a finite mixture model is a non-convex functi...
research
11/15/2017

The landscape of the spiked tensor model

We consider the problem of estimating a large rank-one tensor u^⊗ k∈( R...
research
10/26/2021

On the Optimization Landscape of Maximum Mean Discrepancy

Generative models have been successfully used for generating realistic s...

Please sign up or login with your details

Forgot password? Click here to reset