License: Creative Commons Attribution 3.0 Unported license (CC BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.ITCS.2021.75
URN: urn:nbn:de:0030-drops-136148
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2021/13614/
Go to the corresponding LIPIcs Volume Portal

Holmgren, Justin ; Wein, Alexander S.

Counterexamples to the Low-Degree Conjecture

pdf-format:
LIPIcs-ITCS-2021-75.pdf (0.4 MB)

Abstract

A conjecture of Hopkins (2018) posits that for certain high-dimensional hypothesis testing problems, no polynomial-time algorithm can outperform so-called "simple statistics", which are low-degree polynomials in the data. This conjecture formalizes the beliefs surrounding a line of recent work that seeks to understand statistical-versus-computational tradeoffs via the low-degree likelihood ratio. In this work, we refute the conjecture of Hopkins. However, our counterexample crucially exploits the specifics of the noise operator used in the conjecture, and we point out a simple way to modify the conjecture to rule out our counterexample. We also give an example illustrating that (even after the above modification), the symmetry assumption in the conjecture is necessary. These results do not undermine the low-degree framework for computational lower bounds, but rather aim to better understand what class of problems it is applicable to.

BibTeX - Entry

@InProceedings{holmgren_et_al:LIPIcs.ITCS.2021.75,
  author =	{Justin Holmgren and Alexander S. Wein},
  title =	{{Counterexamples to the Low-Degree Conjecture}},
  booktitle =	{12th Innovations in Theoretical Computer Science Conference (ITCS 2021)},
  pages =	{75:1--75:9},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-177-1},
  ISSN =	{1868-8969},
  year =	{2021},
  volume =	{185},
  editor =	{James R. Lee},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2021/13614},
  URN =		{urn:nbn:de:0030-drops-136148},
  doi =		{10.4230/LIPIcs.ITCS.2021.75},
  annote =	{Keywords: Low-degree likelihood ratio, error-correcting codes}
}

Keywords: Low-degree likelihood ratio, error-correcting codes
Collection: 12th Innovations in Theoretical Computer Science Conference (ITCS 2021)
Issue Date: 2021
Date of publication: 04.02.2021

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI