Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962721953> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2962721953 abstract "We study planted problems-finding hidden structures in random noisy inputs-through the lens of the sum-of-squares semidefinite programming hierarchy (SoS). This family of powerful semidefinite programs has recently yielded many new algorithms for planted problems, often achieving the best known polynomial-time guarantees in terms of accuracy of recovered solutions and robustness to noise. One theme in recent work is the design of spectral algorithms which match the guarantees of SoS algorithms for planted problems. Classical spectral algorithms are often unable to accomplish this: the twist in these new spectral algorithms is the use of spectral structure of matrices whose entries are low-degree polynomials of the input variables. We prove that for a wide class of planted problems, including refuting random constraint satisfaction problems, tensor and sparse PCA, densest-ksubgraph, community detection in stochastic block models, planted clique, and others, eigenvalues of degree-d matrix polynomials are as powerful as SoS semidefinite programs of degree d. For such problems it is therefore always possible to match the guarantees of SoS without solving a large semidefinite program. Using related ideas on SoS algorithms and lowdegree matrix polynomials (and inspired by recent work on SoS and the planted clique problem [BHK <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>+</sup> 16]), we prove a new SoS lower bound for the tensor PCA problem." @default.
- W2962721953 created "2019-07-30" @default.
- W2962721953 creator A5001123654 @default.
- W2962721953 creator A5044412015 @default.
- W2962721953 creator A5053469573 @default.
- W2962721953 creator A5068103506 @default.
- W2962721953 creator A5081583404 @default.
- W2962721953 creator A5089128021 @default.
- W2962721953 date "2017-10-01" @default.
- W2962721953 modified "2023-10-16" @default.
- W2962721953 title "The Power of Sum-of-Squares for Detecting Hidden Structures" @default.
- W2962721953 cites W2012805418 @default.
- W2962721953 cites W2022749269 @default.
- W2962721953 cites W2079035346 @default.
- W2962721953 cites W2080905757 @default.
- W2962721953 cites W2107052785 @default.
- W2962721953 cites W2109154425 @default.
- W2962721953 cites W2138341424 @default.
- W2962721953 cites W2166602562 @default.
- W2962721953 cites W2216459995 @default.
- W2962721953 cites W2290522125 @default.
- W2962721953 cites W2581091247 @default.
- W2962721953 cites W2600945321 @default.
- W2962721953 cites W2962907923 @default.
- W2962721953 cites W2963256102 @default.
- W2962721953 doi "https://doi.org/10.1109/focs.2017.72" @default.
- W2962721953 hasPublicationYear "2017" @default.
- W2962721953 type Work @default.
- W2962721953 sameAs 2962721953 @default.
- W2962721953 citedByCount "71" @default.
- W2962721953 countsByYear W29627219532017 @default.
- W2962721953 countsByYear W29627219532018 @default.
- W2962721953 countsByYear W29627219532019 @default.
- W2962721953 countsByYear W29627219532020 @default.
- W2962721953 countsByYear W29627219532021 @default.
- W2962721953 countsByYear W29627219532022 @default.
- W2962721953 countsByYear W29627219532023 @default.
- W2962721953 crossrefType "proceedings-article" @default.
- W2962721953 hasAuthorship W2962721953A5001123654 @default.
- W2962721953 hasAuthorship W2962721953A5044412015 @default.
- W2962721953 hasAuthorship W2962721953A5053469573 @default.
- W2962721953 hasAuthorship W2962721953A5068103506 @default.
- W2962721953 hasAuthorship W2962721953A5081583404 @default.
- W2962721953 hasAuthorship W2962721953A5089128021 @default.
- W2962721953 hasBestOaLocation W29627219532 @default.
- W2962721953 hasConcept C101901036 @default.
- W2962721953 hasConcept C104317684 @default.
- W2962721953 hasConcept C11413529 @default.
- W2962721953 hasConcept C114614502 @default.
- W2962721953 hasConcept C121332964 @default.
- W2962721953 hasConcept C126255220 @default.
- W2962721953 hasConcept C132525143 @default.
- W2962721953 hasConcept C150997102 @default.
- W2962721953 hasConcept C158693339 @default.
- W2962721953 hasConcept C185592680 @default.
- W2962721953 hasConcept C203776342 @default.
- W2962721953 hasConcept C33923547 @default.
- W2962721953 hasConcept C41008148 @default.
- W2962721953 hasConcept C43517604 @default.
- W2962721953 hasConcept C55493867 @default.
- W2962721953 hasConcept C62520636 @default.
- W2962721953 hasConcept C63479239 @default.
- W2962721953 hasConcept C80444323 @default.
- W2962721953 hasConceptScore W2962721953C101901036 @default.
- W2962721953 hasConceptScore W2962721953C104317684 @default.
- W2962721953 hasConceptScore W2962721953C11413529 @default.
- W2962721953 hasConceptScore W2962721953C114614502 @default.
- W2962721953 hasConceptScore W2962721953C121332964 @default.
- W2962721953 hasConceptScore W2962721953C126255220 @default.
- W2962721953 hasConceptScore W2962721953C132525143 @default.
- W2962721953 hasConceptScore W2962721953C150997102 @default.
- W2962721953 hasConceptScore W2962721953C158693339 @default.
- W2962721953 hasConceptScore W2962721953C185592680 @default.
- W2962721953 hasConceptScore W2962721953C203776342 @default.
- W2962721953 hasConceptScore W2962721953C33923547 @default.
- W2962721953 hasConceptScore W2962721953C41008148 @default.
- W2962721953 hasConceptScore W2962721953C43517604 @default.
- W2962721953 hasConceptScore W2962721953C55493867 @default.
- W2962721953 hasConceptScore W2962721953C62520636 @default.
- W2962721953 hasConceptScore W2962721953C63479239 @default.
- W2962721953 hasConceptScore W2962721953C80444323 @default.
- W2962721953 hasLocation W29627219531 @default.
- W2962721953 hasLocation W29627219532 @default.
- W2962721953 hasOpenAccess W2962721953 @default.
- W2962721953 hasPrimaryLocation W29627219531 @default.
- W2962721953 hasRelatedWork W1520074457 @default.
- W2962721953 hasRelatedWork W1788812054 @default.
- W2962721953 hasRelatedWork W2024507128 @default.
- W2962721953 hasRelatedWork W2092089517 @default.
- W2962721953 hasRelatedWork W2288891047 @default.
- W2962721953 hasRelatedWork W2378309693 @default.
- W2962721953 hasRelatedWork W2381295697 @default.
- W2962721953 hasRelatedWork W2385886188 @default.
- W2962721953 hasRelatedWork W2622496098 @default.
- W2962721953 hasRelatedWork W3166939022 @default.
- W2962721953 isParatext "false" @default.
- W2962721953 isRetracted "false" @default.
- W2962721953 magId "2962721953" @default.
- W2962721953 workType "article" @default.