Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286894975> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4286894975 abstract "Machine learning algorithms based on parametrized quantum circuits are a prime candidate for near-term applications on noisy quantum computers. Yet, our understanding of how these quantum machine learning models compare, both mutually and to classical models, remains limited. Previous works achieved important steps in this direction by showing a close connection between some of these quantum models and kernel methods, well-studied in classical machine learning. In this work, we identify the first unifying framework that captures all standard models based on parametrized quantum circuits: that of linear quantum models. In particular, we show how data re-uploading circuits, a generalization of linear models, can be efficiently mapped into equivalent linear quantum models. Going further, we also consider the experimentally-relevant resource requirements of these models in terms of qubit number and data-sample efficiency, i.e., amount of data needed to learn. We establish learning separations demonstrating that linear quantum models must utilize exponentially more qubits than data re-uploading models in order to solve certain learning tasks, while kernel methods additionally require exponentially many more data points. Our results constitute significant strides towards a more comprehensive theory of quantum machine learning models as well as provide guidelines on which models may be better suited from experimental perspectives." @default.
- W4286894975 created "2022-07-25" @default.
- W4286894975 creator A5009007803 @default.
- W4286894975 creator A5023989415 @default.
- W4286894975 creator A5042661222 @default.
- W4286894975 creator A5043277691 @default.
- W4286894975 creator A5069043772 @default.
- W4286894975 creator A5083810678 @default.
- W4286894975 date "2021-10-25" @default.
- W4286894975 modified "2023-09-26" @default.
- W4286894975 title "Quantum machine learning beyond kernel methods" @default.
- W4286894975 doi "https://doi.org/10.48550/arxiv.2110.13162" @default.
- W4286894975 hasPublicationYear "2021" @default.
- W4286894975 type Work @default.
- W4286894975 citedByCount "2" @default.
- W4286894975 countsByYear W42868949752022 @default.
- W4286894975 countsByYear W42868949752023 @default.
- W4286894975 crossrefType "posted-content" @default.
- W4286894975 hasAuthorship W4286894975A5009007803 @default.
- W4286894975 hasAuthorship W4286894975A5023989415 @default.
- W4286894975 hasAuthorship W4286894975A5042661222 @default.
- W4286894975 hasAuthorship W4286894975A5043277691 @default.
- W4286894975 hasAuthorship W4286894975A5069043772 @default.
- W4286894975 hasAuthorship W4286894975A5083810678 @default.
- W4286894975 hasBestOaLocation W42868949751 @default.
- W4286894975 hasConcept C11413529 @default.
- W4286894975 hasConcept C118615104 @default.
- W4286894975 hasConcept C119857082 @default.
- W4286894975 hasConcept C121332964 @default.
- W4286894975 hasConcept C122280245 @default.
- W4286894975 hasConcept C12267149 @default.
- W4286894975 hasConcept C124148022 @default.
- W4286894975 hasConcept C134306372 @default.
- W4286894975 hasConcept C137019171 @default.
- W4286894975 hasConcept C154945302 @default.
- W4286894975 hasConcept C177148314 @default.
- W4286894975 hasConcept C203087015 @default.
- W4286894975 hasConcept C2779094486 @default.
- W4286894975 hasConcept C33923547 @default.
- W4286894975 hasConcept C41008148 @default.
- W4286894975 hasConcept C51003876 @default.
- W4286894975 hasConcept C62520636 @default.
- W4286894975 hasConcept C74193536 @default.
- W4286894975 hasConcept C80444323 @default.
- W4286894975 hasConcept C84114770 @default.
- W4286894975 hasConceptScore W4286894975C11413529 @default.
- W4286894975 hasConceptScore W4286894975C118615104 @default.
- W4286894975 hasConceptScore W4286894975C119857082 @default.
- W4286894975 hasConceptScore W4286894975C121332964 @default.
- W4286894975 hasConceptScore W4286894975C122280245 @default.
- W4286894975 hasConceptScore W4286894975C12267149 @default.
- W4286894975 hasConceptScore W4286894975C124148022 @default.
- W4286894975 hasConceptScore W4286894975C134306372 @default.
- W4286894975 hasConceptScore W4286894975C137019171 @default.
- W4286894975 hasConceptScore W4286894975C154945302 @default.
- W4286894975 hasConceptScore W4286894975C177148314 @default.
- W4286894975 hasConceptScore W4286894975C203087015 @default.
- W4286894975 hasConceptScore W4286894975C2779094486 @default.
- W4286894975 hasConceptScore W4286894975C33923547 @default.
- W4286894975 hasConceptScore W4286894975C41008148 @default.
- W4286894975 hasConceptScore W4286894975C51003876 @default.
- W4286894975 hasConceptScore W4286894975C62520636 @default.
- W4286894975 hasConceptScore W4286894975C74193536 @default.
- W4286894975 hasConceptScore W4286894975C80444323 @default.
- W4286894975 hasConceptScore W4286894975C84114770 @default.
- W4286894975 hasLocation W42868949751 @default.
- W4286894975 hasOpenAccess W4286894975 @default.
- W4286894975 hasPrimaryLocation W42868949751 @default.
- W4286894975 hasRelatedWork W10287351 @default.
- W4286894975 hasRelatedWork W11644230 @default.
- W4286894975 hasRelatedWork W13953375 @default.
- W4286894975 hasRelatedWork W14789944 @default.
- W4286894975 hasRelatedWork W5557673 @default.
- W4286894975 hasRelatedWork W6229082 @default.
- W4286894975 hasRelatedWork W6533109 @default.
- W4286894975 hasRelatedWork W6717794 @default.
- W4286894975 hasRelatedWork W7177339 @default.
- W4286894975 hasRelatedWork W8728285 @default.
- W4286894975 isParatext "false" @default.
- W4286894975 isRetracted "false" @default.
- W4286894975 workType "article" @default.