FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380490505> ?p ?o ?g. }

• W4380490505 abstract "Structural matrix-variate observations routinely arise in diverse fields such as multilayer network analysis and brain image clustering. While data of this type have been extensively investigated with fruitful outcomes being delivered, the fundamental questions like its statistical optimality and computational limit are largely under-explored. In this paper, we propose a low-rank Gaussian mixture model (LrMM) assuming each matrix-valued observation has a planted low-rank structure. Minimax lower bounds for estimating the underlying low-rank matrix are established allowing a whole range of sample sizes and signal strength. Under a minimal condition on signal strength, referred to as the information-theoretical limit or statistical limit, we prove the minimax optimality of a maximum likelihood estimator which, in general, is computationally infeasible. If the signal is stronger than a certain threshold, called the computational limit, we design a computationally fast estimator based on spectral aggregation and demonstrate its minimax optimality. Moreover, when the signal strength is smaller than the computational limit, we provide evidences based on the low-degree likelihood ratio framework to claim that no polynomial-time algorithm can consistently recover the underlying low-rank matrix. Our results reveal multiple phase transitions in the minimax error rates and the statistical-to-computational gap. Numerical experiments confirm our theoretical findings. We further showcase the merit of our spectral aggregation method on the worldwide food trading dataset." @default.
• W4380490505 created "2023-06-14" @default.
• W4380490505 creator A5028253321 @default.
• W4380490505 creator A5056492561 @default.
• W4380490505 date "2023-04-01" @default.
• W4380490505 modified "2023-10-01" @default.
• W4380490505 title "Optimal estimation and computational limit of low-rank Gaussian mixtures" @default.
• W4380490505 cites W1584961538 @default.
• W4380490505 cites W1650743651 @default.
• W4380490505 cites W1963566461 @default.
• W4380490505 cites W1965745576 @default.
• W4380490505 cites W1969015668 @default.
• W4380490505 cites W2010353172 @default.
• W4380490505 cites W2022852240 @default.
• W4380490505 cites W2026302946 @default.
• W4380490505 cites W2030361786 @default.
• W4380490505 cites W2047064469 @default.
• W4380490505 cites W2051387260 @default.
• W4380490505 cites W2060195349 @default.
• W4380490505 cites W2123583562 @default.
• W4380490505 cites W2133097426 @default.
• W4380490505 cites W2133755908 @default.
• W4380490505 cites W2134265283 @default.
• W4380490505 cites W2287818844 @default.
• W4380490505 cites W2409448157 @default.
• W4380490505 cites W2553813354 @default.
• W4380490505 cites W2726993892 @default.
• W4380490505 cites W2797390835 @default.
• W4380490505 cites W2911742394 @default.
• W4380490505 cites W2950009848 @default.
• W4380490505 cites W2962737134 @default.
• W4380490505 cites W2962967150 @default.
• W4380490505 cites W2963256582 @default.
• W4380490505 cites W2963780177 @default.
• W4380490505 cites W2964066048 @default.
• W4380490505 cites W2964738308 @default.
• W4380490505 cites W2970227627 @default.
• W4380490505 cites W2980451193 @default.
• W4380490505 cites W3005819971 @default.
• W4380490505 cites W3006912604 @default.
• W4380490505 cites W3028265701 @default.
• W4380490505 cites W3049253527 @default.
• W4380490505 cites W3049391701 @default.
• W4380490505 cites W3110212018 @default.
• W4380490505 cites W3127320487 @default.
• W4380490505 cites W3136301269 @default.
• W4380490505 cites W3136777397 @default.
• W4380490505 cites W3187218931 @default.
• W4380490505 cites W3200992793 @default.
• W4380490505 cites W3211977733 @default.
• W4380490505 cites W4301425558 @default.
• W4380490505 doi "https://doi.org/10.1214/23-aos2264" @default.
• W4380490505 hasPublicationYear "2023" @default.
• W4380490505 type Work @default.
• W4380490505 citedByCount "0" @default.
• W4380490505 crossrefType "journal-article" @default.
• W4380490505 hasAuthorship W4380490505A5028253321 @default.
• W4380490505 hasAuthorship W4380490505A5056492561 @default.
• W4380490505 hasBestOaLocation W43804905052 @default.
• W4380490505 hasConcept C105795698 @default.
• W4380490505 hasConcept C106487976 @default.
• W4380490505 hasConcept C11413529 @default.
• W4380490505 hasConcept C114614502 @default.
• W4380490505 hasConcept C121332964 @default.
• W4380490505 hasConcept C126255220 @default.
• W4380490505 hasConcept C134306372 @default.
• W4380490505 hasConcept C149728462 @default.
• W4380490505 hasConcept C151201525 @default.
• W4380490505 hasConcept C155281189 @default.
• W4380490505 hasConcept C158693339 @default.
• W4380490505 hasConcept C159985019 @default.
• W4380490505 hasConcept C163716315 @default.
• W4380490505 hasConcept C164226766 @default.
• W4380490505 hasConcept C179799912 @default.
• W4380490505 hasConcept C185429906 @default.
• W4380490505 hasConcept C192562407 @default.
• W4380490505 hasConcept C202444582 @default.
• W4380490505 hasConcept C204323151 @default.
• W4380490505 hasConcept C28826006 @default.
• W4380490505 hasConcept C33923547 @default.
• W4380490505 hasConcept C62520636 @default.
• W4380490505 hasConcept C64812099 @default.
• W4380490505 hasConcept C90199385 @default.
• W4380490505 hasConceptScore W4380490505C105795698 @default.
• W4380490505 hasConceptScore W4380490505C106487976 @default.
• W4380490505 hasConceptScore W4380490505C11413529 @default.
• W4380490505 hasConceptScore W4380490505C114614502 @default.
• W4380490505 hasConceptScore W4380490505C121332964 @default.
• W4380490505 hasConceptScore W4380490505C126255220 @default.
• W4380490505 hasConceptScore W4380490505C134306372 @default.
• W4380490505 hasConceptScore W4380490505C149728462 @default.
• W4380490505 hasConceptScore W4380490505C151201525 @default.
• W4380490505 hasConceptScore W4380490505C155281189 @default.
• W4380490505 hasConceptScore W4380490505C158693339 @default.
• W4380490505 hasConceptScore W4380490505C159985019 @default.
• W4380490505 hasConceptScore W4380490505C163716315 @default.
• W4380490505 hasConceptScore W4380490505C164226766 @default.
• W4380490505 hasConceptScore W4380490505C179799912 @default.
• W4380490505 hasConceptScore W4380490505C185429906 @default.
• W4380490505 hasConceptScore W4380490505C192562407 @default.

• next