Matches in SemOpenAlex for { <https://semopenalex.org/work/W4372280129> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4372280129 abstract "Quantum generative models, in providing inherently efficient sampling strategies, show promise for achieving a near-term advantage on quantum hardware. Nonetheless, important questions remain regarding their scalability. In this work, we investigate the barriers to the trainability of quantum generative models posed by barren plateaus and exponential loss concentration. We explore the interplay between explicit and implicit models and losses, and show that using implicit generative models (such as quantum circuit-based models) with explicit losses (such as the KL divergence) leads to a new flavour of barren plateau. In contrast, the Maximum Mean Discrepancy (MMD), which is a popular example of an implicit loss, can be viewed as the expectation value of an observable that is either low-bodied and trainable, or global and untrainable depending on the choice of kernel. However, in parallel, we highlight that the low-bodied losses required for trainability cannot in general distinguish high-order correlations, leading to a fundamental tension between exponential concentration and the emergence of spurious minima. We further propose a new local quantum fidelity-type loss which, by leveraging quantum circuits to estimate the quality of the encoded distribution, is both faithful and enjoys trainability guarantees. Finally, we compare the performance of different loss functions for modelling real-world data from the High-Energy-Physics domain and confirm the trends predicted by our theoretical results." @default.
- W4372280129 created "2023-05-07" @default.
- W4372280129 creator A5001923006 @default.
- W4372280129 creator A5015891572 @default.
- W4372280129 creator A5017741513 @default.
- W4372280129 creator A5059600722 @default.
- W4372280129 creator A5068470039 @default.
- W4372280129 creator A5071652167 @default.
- W4372280129 creator A5085844215 @default.
- W4372280129 date "2023-05-04" @default.
- W4372280129 modified "2023-09-27" @default.
- W4372280129 title "Trainability barriers and opportunities in quantum generative modeling" @default.
- W4372280129 doi "https://doi.org/10.48550/arxiv.2305.02881" @default.
- W4372280129 hasPublicationYear "2023" @default.
- W4372280129 type Work @default.
- W4372280129 citedByCount "0" @default.
- W4372280129 crossrefType "posted-content" @default.
- W4372280129 hasAuthorship W4372280129A5001923006 @default.
- W4372280129 hasAuthorship W4372280129A5015891572 @default.
- W4372280129 hasAuthorship W4372280129A5017741513 @default.
- W4372280129 hasAuthorship W4372280129A5059600722 @default.
- W4372280129 hasAuthorship W4372280129A5068470039 @default.
- W4372280129 hasAuthorship W4372280129A5071652167 @default.
- W4372280129 hasAuthorship W4372280129A5085844215 @default.
- W4372280129 hasBestOaLocation W43722801291 @default.
- W4372280129 hasConcept C119857082 @default.
- W4372280129 hasConcept C121332964 @default.
- W4372280129 hasConcept C121864883 @default.
- W4372280129 hasConcept C134306372 @default.
- W4372280129 hasConcept C138885662 @default.
- W4372280129 hasConcept C154945302 @default.
- W4372280129 hasConcept C167966045 @default.
- W4372280129 hasConcept C186633575 @default.
- W4372280129 hasConcept C207390915 @default.
- W4372280129 hasConcept C2779094486 @default.
- W4372280129 hasConcept C32848918 @default.
- W4372280129 hasConcept C33923547 @default.
- W4372280129 hasConcept C39890363 @default.
- W4372280129 hasConcept C41008148 @default.
- W4372280129 hasConcept C41895202 @default.
- W4372280129 hasConcept C48044578 @default.
- W4372280129 hasConcept C58053490 @default.
- W4372280129 hasConcept C62520636 @default.
- W4372280129 hasConcept C77088390 @default.
- W4372280129 hasConcept C80444323 @default.
- W4372280129 hasConcept C84114770 @default.
- W4372280129 hasConcept C97256817 @default.
- W4372280129 hasConceptScore W4372280129C119857082 @default.
- W4372280129 hasConceptScore W4372280129C121332964 @default.
- W4372280129 hasConceptScore W4372280129C121864883 @default.
- W4372280129 hasConceptScore W4372280129C134306372 @default.
- W4372280129 hasConceptScore W4372280129C138885662 @default.
- W4372280129 hasConceptScore W4372280129C154945302 @default.
- W4372280129 hasConceptScore W4372280129C167966045 @default.
- W4372280129 hasConceptScore W4372280129C186633575 @default.
- W4372280129 hasConceptScore W4372280129C207390915 @default.
- W4372280129 hasConceptScore W4372280129C2779094486 @default.
- W4372280129 hasConceptScore W4372280129C32848918 @default.
- W4372280129 hasConceptScore W4372280129C33923547 @default.
- W4372280129 hasConceptScore W4372280129C39890363 @default.
- W4372280129 hasConceptScore W4372280129C41008148 @default.
- W4372280129 hasConceptScore W4372280129C41895202 @default.
- W4372280129 hasConceptScore W4372280129C48044578 @default.
- W4372280129 hasConceptScore W4372280129C58053490 @default.
- W4372280129 hasConceptScore W4372280129C62520636 @default.
- W4372280129 hasConceptScore W4372280129C77088390 @default.
- W4372280129 hasConceptScore W4372280129C80444323 @default.
- W4372280129 hasConceptScore W4372280129C84114770 @default.
- W4372280129 hasConceptScore W4372280129C97256817 @default.
- W4372280129 hasLocation W43722801291 @default.
- W4372280129 hasOpenAccess W4372280129 @default.
- W4372280129 hasPrimaryLocation W43722801291 @default.
- W4372280129 hasRelatedWork W2963654820 @default.
- W4372280129 hasRelatedWork W2982171823 @default.
- W4372280129 hasRelatedWork W3094453214 @default.
- W4372280129 hasRelatedWork W3106525485 @default.
- W4372280129 hasRelatedWork W3172189297 @default.
- W4372280129 hasRelatedWork W3203554004 @default.
- W4372280129 hasRelatedWork W4221160981 @default.
- W4372280129 hasRelatedWork W4286977204 @default.
- W4372280129 hasRelatedWork W4287024609 @default.
- W4372280129 hasRelatedWork W4321012214 @default.
- W4372280129 isParatext "false" @default.
- W4372280129 isRetracted "false" @default.
- W4372280129 workType "article" @default.