How to Decompose a Tensor with Group Structure

06/04/2021
by   Allen Liu, et al.
0

In this work we study the orbit recovery problem, which is a natural abstraction for the problem of recovering a planted signal from noisy measurements under unknown group actions. Many important inverse problems in statistics, engineering and the sciences fit into this framework. Prior work has studied cases when the group is discrete and/or abelian. However fundamentally new techniques are needed in order to handle more complex group actions. Our main result is a quasi-polynomial time algorithm to solve orbit recovery over SO(3) - i.e. the cryo-electron tomography problem which asks to recover the three-dimensional structure of a molecule from noisy measurements of randomly rotated copies of it. We analyze a variant of the frequency marching heuristic in the framework of smoothed analysis. Our approach exploits the layered structure of the invariant polynomials, and simultaneously yields a new class of tensor decomposition algorithms that work in settings when the tensor is not low-rank but rather where the factors are algebraically related to each other by a group action.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/21/2015

Decomposing Overcomplete 3rd Order Tensors using Sum-of-Squares Algorithms

Tensor rank and low-rank tensor decompositions have many applications in...
research
11/02/2018

Spectral Methods from Tensor Networks

A tensor network is a diagram that specifies a way to "multiply" a colle...
research
10/28/2021

Approximately low-rank recovery from noisy and local measurements by convex program

Low-rank matrix models have been universally useful for numerous applica...
research
10/29/2022

The isotropy group of the matrix multiplication tensor

By an isotropy group of a tensor t∈ V_1 ⊗ V_2⊗ V_3=V we mean the group o...
research
08/05/2020

Computational Barriers to Estimation from Low-Degree Polynomials

One fundamental goal of high-dimensional statistics is to detect or reco...
research
06/11/2021

Dictionary and prior learning with unrolled algorithms for unsupervised inverse problems

Inverse problems consist in recovering a signal given noisy observations...
research
06/26/2021

Recovery from Power Sums

We study the problem of recovering a collection of n numbers from the ev...

Please sign up or login with your details

Forgot password? Click here to reset