Computational Complexity of Statistics: New Insights from Low-Degree Polynomials

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Wein, Alexander S.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909647048278016
author Wein, Alexander S.
author_facet Wein, Alexander S.
contents This is a survey on the use of low-degree polynomials to predict and explain the apparent statistical-computational tradeoffs in a variety of average-case computational problems. In a nutshell, this framework measures the complexity of a statistical task by the minimum degree that a polynomial function must have in order to solve it. The main goals of this survey are to (1) describe the types of problems where the low-degree framework can be applied, encompassing questions of detection (hypothesis testing), recovery (estimation), and more; (2) discuss some philosophical questions surrounding the interpretation of low-degree lower bounds, and notably the extent to which they should be treated as evidence for inherent computational hardness; (3) explore the known connections between low-degree polynomials and other related approaches such as the sum-of-squares hierarchy and statistical query model; and (4) give an overview of the mathematical tools used to prove low-degree lower bounds. A list of open problems is also included.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10748
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Computational Complexity of Statistics: New Insights from Low-Degree Polynomials
Wein, Alexander S.
Statistics Theory
Computational Complexity
Machine Learning
This is a survey on the use of low-degree polynomials to predict and explain the apparent statistical-computational tradeoffs in a variety of average-case computational problems. In a nutshell, this framework measures the complexity of a statistical task by the minimum degree that a polynomial function must have in order to solve it. The main goals of this survey are to (1) describe the types of problems where the low-degree framework can be applied, encompassing questions of detection (hypothesis testing), recovery (estimation), and more; (2) discuss some philosophical questions surrounding the interpretation of low-degree lower bounds, and notably the extent to which they should be treated as evidence for inherent computational hardness; (3) explore the known connections between low-degree polynomials and other related approaches such as the sum-of-squares hierarchy and statistical query model; and (4) give an overview of the mathematical tools used to prove low-degree lower bounds. A list of open problems is also included.
title Computational Complexity of Statistics: New Insights from Low-Degree Polynomials
topic Statistics Theory
Computational Complexity
Machine Learning
url https://arxiv.org/abs/2506.10748