Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320342541> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4320342541 abstract "We develop new tools in the theory of nonlinear random matrices and apply them to study the performance of the Sum of Squares (SoS) hierarchy on average-case problems. The SoS hierarchy is a powerful optimization technique that has achieved tremendous success for various problems in combinatorial optimization, robust statistics and machine learning. It's a family of convex relaxations that lets us smoothly trade off running time for approximation guarantees. In recent works, it's been shown to be extremely useful for recovering structure in high dimensional noisy data. It also remains our best approach towards refuting the notorious Unique Games Conjecture. In this work, we analyze the performance of the SoS hierarchy on fundamental problems stemming from statistics, theoretical computer science and statistical physics. In particular, we show subexponential-time SoS lower bounds for the problems of the Sherrington-Kirkpatrick Hamiltonian, Planted Slightly Denser Subgraph, Tensor Principal Components Analysis and Sparse Principal Components Analysis. These SoS lower bounds involve analyzing large random matrices, wherein lie our main contributions. These results offer strong evidence for the truth of and insight into the low-degree likelihood ratio hypothesis, an important conjecture that predicts the power of bounded-time algorithms for hypothesis testing. We also develop general-purpose tools for analyzing the behavior of random matrices which are functions of independent random variables. Towards this, we build on and generalize the matrix variant of the Efron-Stein inequalities. In particular, our general theorem on matrix concentration recovers various results that have appeared in the literature. We expect these random matrix theory ideas to have other significant applications." @default.
- W4320342541 created "2023-02-13" @default.
- W4320342541 creator A5052261991 @default.
- W4320342541 date "2023-02-09" @default.
- W4320342541 modified "2023-09-23" @default.
- W4320342541 title "Nonlinear Random Matrices and Applications to the Sum of Squares Hierarchy" @default.
- W4320342541 doi "https://doi.org/10.48550/arxiv.2302.04462" @default.
- W4320342541 hasPublicationYear "2023" @default.
- W4320342541 type Work @default.
- W4320342541 citedByCount "0" @default.
- W4320342541 crossrefType "posted-content" @default.
- W4320342541 hasAuthorship W4320342541A5052261991 @default.
- W4320342541 hasBestOaLocation W43203425411 @default.
- W4320342541 hasConcept C105795698 @default.
- W4320342541 hasConcept C106487976 @default.
- W4320342541 hasConcept C118615104 @default.
- W4320342541 hasConcept C121332964 @default.
- W4320342541 hasConcept C126255220 @default.
- W4320342541 hasConcept C134306372 @default.
- W4320342541 hasConcept C158622935 @default.
- W4320342541 hasConcept C158693339 @default.
- W4320342541 hasConcept C159985019 @default.
- W4320342541 hasConcept C162324750 @default.
- W4320342541 hasConcept C192562407 @default.
- W4320342541 hasConcept C2780990831 @default.
- W4320342541 hasConcept C28826006 @default.
- W4320342541 hasConcept C31170391 @default.
- W4320342541 hasConcept C33923547 @default.
- W4320342541 hasConcept C34388435 @default.
- W4320342541 hasConcept C34447519 @default.
- W4320342541 hasConcept C41008148 @default.
- W4320342541 hasConcept C49847556 @default.
- W4320342541 hasConcept C62520636 @default.
- W4320342541 hasConcept C64812099 @default.
- W4320342541 hasConceptScore W4320342541C105795698 @default.
- W4320342541 hasConceptScore W4320342541C106487976 @default.
- W4320342541 hasConceptScore W4320342541C118615104 @default.
- W4320342541 hasConceptScore W4320342541C121332964 @default.
- W4320342541 hasConceptScore W4320342541C126255220 @default.
- W4320342541 hasConceptScore W4320342541C134306372 @default.
- W4320342541 hasConceptScore W4320342541C158622935 @default.
- W4320342541 hasConceptScore W4320342541C158693339 @default.
- W4320342541 hasConceptScore W4320342541C159985019 @default.
- W4320342541 hasConceptScore W4320342541C162324750 @default.
- W4320342541 hasConceptScore W4320342541C192562407 @default.
- W4320342541 hasConceptScore W4320342541C2780990831 @default.
- W4320342541 hasConceptScore W4320342541C28826006 @default.
- W4320342541 hasConceptScore W4320342541C31170391 @default.
- W4320342541 hasConceptScore W4320342541C33923547 @default.
- W4320342541 hasConceptScore W4320342541C34388435 @default.
- W4320342541 hasConceptScore W4320342541C34447519 @default.
- W4320342541 hasConceptScore W4320342541C41008148 @default.
- W4320342541 hasConceptScore W4320342541C49847556 @default.
- W4320342541 hasConceptScore W4320342541C62520636 @default.
- W4320342541 hasConceptScore W4320342541C64812099 @default.
- W4320342541 hasLocation W43203425411 @default.
- W4320342541 hasOpenAccess W4320342541 @default.
- W4320342541 hasPrimaryLocation W43203425411 @default.
- W4320342541 hasRelatedWork W1506854270 @default.
- W4320342541 hasRelatedWork W1994833872 @default.
- W4320342541 hasRelatedWork W1999551182 @default.
- W4320342541 hasRelatedWork W2046365279 @default.
- W4320342541 hasRelatedWork W2060857373 @default.
- W4320342541 hasRelatedWork W2351811947 @default.
- W4320342541 hasRelatedWork W3038654277 @default.
- W4320342541 hasRelatedWork W3080875783 @default.
- W4320342541 hasRelatedWork W4213212592 @default.
- W4320342541 hasRelatedWork W4298324236 @default.
- W4320342541 isParatext "false" @default.
- W4320342541 isRetracted "false" @default.
- W4320342541 workType "article" @default.