Symmetric Tensor Completion from Multilinear Entries and Learning Product Mixtures over the Hypercube

06/09/2015
by   Tselil Schramm, et al.
0

We give an algorithm for completing an order-m symmetric low-rank tensor from its multilinear entries in time roughly proportional to the number of tensor entries. We apply our tensor completion algorithm to the problem of learning mixtures of product distributions over the hypercube, obtaining new algorithmic results. If the centers of the product distribution are linearly independent, then we recover distributions with as many as Ω(n) centers in polynomial time and sample complexity. In the general case, we recover distributions with as many as Ω̃(n) centers in quasi-polynomial time, answering an open problem of Feldman et al. (SIAM J. Comp.) for the special case of distributions with incoherent bias vectors. Our main algorithmic tool is the iterated application of a low-rank matrix completion algorithm for matrices with adversarially missing entries.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/12/2013

Learning Mixtures of Discrete Product Distributions using Spectral Decompositions

We study the problem of learning a distribution from samples, when the u...
research
04/17/2013

Low-Rank Matrix and Tensor Completion via Adaptive Sampling

We study low rank matrix and tensor completion and propose novel algorit...
research
09/14/2019

Typical ranks in symmetric matrix completion

We study the problem of low-rank matrix completion for symmetric matrice...
research
02/18/2021

Recovering orthogonal tensors under arbitrarily strong, but locally correlated, noise

We consider the problem of recovering an orthogonally decomposable tenso...
research
02/21/2017

Exact tensor completion with sum-of-squares

We obtain the first polynomial-time algorithm for exact tensor completio...
research
07/12/2023

Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective

Obtaining rigorous statistical guarantees for generalization under distr...
research
02/27/2017

Faster Tensor Canonicalization

The Butler-Portugal algorithm for obtaining the canonical form of a tens...

Please sign up or login with your details

Forgot password? Click here to reset