FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3033846281> ?p ?o ?g. }

• W3033846281 abstract "Generative neural networks have been empirically found very promising in providing effective structural priors for compressed sensing, since they can be trained to span low-dimensional data manifolds in high-dimensional signal spaces. Despite the non-convexity of the resulting optimization problem, it has also been shown theoretically that, for neural networks with random Gaussian weights, a signal in the range of the network can be efficiently, approximately recovered from a few noisy measurements. However, a major bottleneck of these theoretical guarantees is a network expansivity condition: that each layer of the neural network must be larger than the previous by a logarithmic factor. Our main contribution is to break this strong expansivity assumption, showing that constant expansivity suffices to get efficient recovery algorithms, besides it also being information-theoretically necessary. To overcome the theoretical bottleneck in existing approaches we prove a novel uniform concentration theorem for random functions that might not be Lipschitz but satisfy a relaxed notion which we call pseudo-Lipschitzness. Using this theorem we can show that a matrix concentration inequality known as the Weight Distribution Condition (WDC), which was previously only known to hold for Gaussian matrices with logarithmic aspect ratio, in fact holds for constant aspect ratios too. Since the WDC is a fundamental matrix concentration inequality in the heart of all existing theoretical guarantees on this problem, our tighter bound immediately yields improvements in all known results in the literature on compressed sensing with deep generative priors, including one-bit recovery, phase retrieval, low-rank matrix recovery, and more." @default.
• W3033846281 created "2020-06-12" @default.
• W3033846281 creator A5034822411 @default.
• W3033846281 creator A5036102061 @default.
• W3033846281 creator A5083461583 @default.
• W3033846281 date "2020-06-07" @default.
• W3033846281 modified "2023-10-01" @default.
• W3033846281 title "Constant-Expansion Suffices for Compressed Sensing with Generative Priors" @default.
• W3033846281 cites W2099471712 @default.
• W3033846281 cites W2131172946 @default.
• W3033846281 cites W2164452299 @default.
• W3033846281 cites W2595294663 @default.
• W3033846281 cites W2766527293 @default.
• W3033846281 cites W2804097535 @default.
• W3033846281 cites W2808361645 @default.
• W3033846281 cites W2890223728 @default.
• W3033846281 cites W2893749619 @default.
• W3033846281 cites W2903807915 @default.
• W3033846281 cites W2963139417 @default.
• W3033846281 cites W2963341557 @default.
• W3033846281 cites W2964013315 @default.
• W3033846281 cites W2966991718 @default.
• W3033846281 cites W2967360854 @default.
• W3033846281 cites W2970188304 @default.
• W3033846281 cites W3025242627 @default.
• W3033846281 cites W3034515071 @default.
• W3033846281 cites W3098803551 @default.
• W3033846281 cites W3113425034 @default.
• W3033846281 cites W648143168 @default.
• W3033846281 cites W948098727 @default.
• W3033846281 hasPublicationYear "2020" @default.
• W3033846281 type Work @default.
• W3033846281 sameAs 3033846281 @default.
• W3033846281 citedByCount "2" @default.
• W3033846281 countsByYear W30338462812020 @default.
• W3033846281 countsByYear W30338462812021 @default.
• W3033846281 crossrefType "posted-content" @default.
• W3033846281 hasAuthorship W3033846281A5034822411 @default.
• W3033846281 hasAuthorship W3033846281A5036102061 @default.
• W3033846281 hasAuthorship W3033846281A5083461583 @default.
• W3033846281 hasConcept C106487976 @default.
• W3033846281 hasConcept C107673813 @default.
• W3033846281 hasConcept C11413529 @default.
• W3033846281 hasConcept C121332964 @default.
• W3033846281 hasConcept C124851039 @default.
• W3033846281 hasConcept C126255220 @default.
• W3033846281 hasConcept C134306372 @default.
• W3033846281 hasConcept C149635348 @default.
• W3033846281 hasConcept C154945302 @default.
• W3033846281 hasConcept C158693339 @default.
• W3033846281 hasConcept C159985019 @default.
• W3033846281 hasConcept C163716315 @default.
• W3033846281 hasConcept C177769412 @default.
• W3033846281 hasConcept C192562407 @default.
• W3033846281 hasConcept C199360897 @default.
• W3033846281 hasConcept C22324862 @default.
• W3033846281 hasConcept C2777027219 @default.
• W3033846281 hasConcept C2780513914 @default.
• W3033846281 hasConcept C28826006 @default.
• W3033846281 hasConcept C33923547 @default.
• W3033846281 hasConcept C39927690 @default.
• W3033846281 hasConcept C41008148 @default.
• W3033846281 hasConcept C50644808 @default.
• W3033846281 hasConcept C62520636 @default.
• W3033846281 hasConcept C64812099 @default.
• W3033846281 hasConceptScore W3033846281C106487976 @default.
• W3033846281 hasConceptScore W3033846281C107673813 @default.
• W3033846281 hasConceptScore W3033846281C11413529 @default.
• W3033846281 hasConceptScore W3033846281C121332964 @default.
• W3033846281 hasConceptScore W3033846281C124851039 @default.
• W3033846281 hasConceptScore W3033846281C126255220 @default.
• W3033846281 hasConceptScore W3033846281C134306372 @default.
• W3033846281 hasConceptScore W3033846281C149635348 @default.
• W3033846281 hasConceptScore W3033846281C154945302 @default.
• W3033846281 hasConceptScore W3033846281C158693339 @default.
• W3033846281 hasConceptScore W3033846281C159985019 @default.
• W3033846281 hasConceptScore W3033846281C163716315 @default.
• W3033846281 hasConceptScore W3033846281C177769412 @default.
• W3033846281 hasConceptScore W3033846281C192562407 @default.
• W3033846281 hasConceptScore W3033846281C199360897 @default.
• W3033846281 hasConceptScore W3033846281C22324862 @default.
• W3033846281 hasConceptScore W3033846281C2777027219 @default.
• W3033846281 hasConceptScore W3033846281C2780513914 @default.
• W3033846281 hasConceptScore W3033846281C28826006 @default.
• W3033846281 hasConceptScore W3033846281C33923547 @default.
• W3033846281 hasConceptScore W3033846281C39927690 @default.
• W3033846281 hasConceptScore W3033846281C41008148 @default.
• W3033846281 hasConceptScore W3033846281C50644808 @default.
• W3033846281 hasConceptScore W3033846281C62520636 @default.
• W3033846281 hasConceptScore W3033846281C64812099 @default.
• W3033846281 hasLocation W30338462811 @default.
• W3033846281 hasOpenAccess W3033846281 @default.
• W3033846281 hasPrimaryLocation W30338462811 @default.
• W3033846281 hasRelatedWork W2107822587 @default.
• W3033846281 hasRelatedWork W2594441185 @default.
• W3033846281 hasRelatedWork W2595346029 @default.
• W3033846281 hasRelatedWork W2748447781 @default.
• W3033846281 hasRelatedWork W2795822951 @default.
• W3033846281 hasRelatedWork W2798157611 @default.
• W3033846281 hasRelatedWork W2900591790 @default.

• next