Polynomial-Time Power-Sum Decomposition of Polynomials

TL;DR

This paper presents efficient algorithms for polynomial power-sum decomposition, improving upon prior work by handling larger component sets, lower degrees, and noise robustness using linear algebra and derivative subspace analysis.

Contribution

It introduces a new method for decomposing polynomials into power sums with improved bounds, applicable to quadratic and higher degrees, with robustness to noise.

Findings

Successfully decomposes up to O(n) quadratic components for d=3

Handles polynomial degree d with m  n^{2d/15} components

Robust to inverse polynomial noise with random Gaussian coefficients

Abstract

We give efficient algorithms for finding power-sum decomposition of an input polynomial $P(x)= \sum_{i\leq m} p_i(x)^d$ with component $p_i$s. The case of linear $p_i$s is equivalent to the well-studied tensor decomposition problem while the quadratic case occurs naturally in studying identifiability of non-spherical Gaussian mixtures from low-order moments. Unlike tensor decomposition, both the unique identifiability and algorithms for this problem are not well-understood. For the simplest setting of quadratic $p_i$s and $d=3$, prior work of Ge, Huang and Kakade yields an algorithm only when $m \leq \tilde{O}(\sqrt{n})$. On the other hand, the more general recent result of Garg, Kayal and Saha builds an algebraic approach to handle any $m=n^{O(1)}$ components but only when $d$ is large enough (while yielding no bounds for $d=3$ or even $d=100$) and only handles an inverse exponential noise. Our results obtain a substantial quantitative improvement on both the prior works above even in the base case of $d=3$ and quadratic $p_i$s. Specifically, our algorithm succeeds in decomposing a sum of $m \sim \tilde{O}(n)$ generic quadratic $p_i$s for $d=3$ and more generally the $d$th power-sum of $m \sim n^{2d/15}$ generic degree-$K$ polynomials for any $K \geq 2$. Our algorithm relies only on basic numerical linear algebraic primitives, is exact (i.e., obtain arbitrarily tiny error up to numerical precision), and handles an inverse polynomial noise when the $p_i$s have random Gaussian coefficients. Our main tool is a new method for extracting the linear span of $p_i$s by studying the linear subspace of low-order partial derivatives of the input $P$. For establishing polynomial stability of our algorithm in average-case, we prove inverse polynomial bounds on the smallest singular value of certain correlated random matrices with low-degree polynomial entries that arise in our analyses.