A Nearly Tight Sum-of-Squares Lower Bound for the Planted Clique Problem
Author(s)
Barak, Boaz; Hopkins, Samuel B.; Kothari, Pravesh; Potechin, Aaron; Moitra, Ankur; Kelner, Jonathan Adam; ... Show more Show less
Download1604.03084v2.pdf (708.2Kb)
OPEN_ACCESS_POLICY
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Terms of use
Metadata
Show full item recordAbstract
We prove that with high probability over the choice of a random graph G from the Erds-Rényi distribution G(n,1/2), the n[superscript o(d)]-time degree d Sum-of-Squares semidefinite programming relaxation for the clique problem will give a value of at least n[superscript 1/2-c(d/log n)1/2] for some constant c > 0. This yields a nearly tight n[superscript 1/2-o(1))] bound on the value of this program for any degree d = o(log n). Moreover we introduce a new framework that we call pseudo-calibration to construct Sum-of-Squares lower bounds. This framework is inspired by taking a computational analogue of Bayesian probability theory. It yields a general recipe for constructing good pseudo-distributions (i.e., dual certificates for the Sum-of-Squares semidefinite program), and sheds further light on the ways in which this hierarchy differs from others.
Date issued
2016-12Department
Massachusetts Institute of Technology. Department of MathematicsJournal
2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Barak, Boaz, et al. "A Nearly Tight Sum-of-Squares Lower Bound for the Planted Clique Problem." 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS), 9-11 October, 2016, New Brunswick, New Jersey, IEEE, 2016 © 2016 IEEE
Version: Original manuscript
ISBN
978-1-5090-3933-3