FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376609818> ?p ?o ?g. }

• W4376609818 abstract "Abstract A new paradigm for data science has emerged, with quantum data, quantum models, and quantum computational devices. This field, called quantum machine learning (QML), aims to achieve a speedup over traditional machine learning for data analysis. However, its success usually hinges on efficiently training the parameters in quantum neural networks, and the field of QML is still lacking theoretical scaling results for their trainability. Some trainability results have been proven for a closely related field called variational quantum algorithms (VQAs). While both fields involve training a parametrized quantum circuit, there are crucial differences that make the results for one setting not readily applicable to the other. In this work, we bridge the two frameworks and show that gradient scaling results for VQAs can also be applied to study the gradient scaling of QML models. Our results indicate that features deemed detrimental for VQA trainability can also lead to issues such as barren plateaus in QML. Consequently, our work has implications for several QML proposals in the literature. In addition, we provide theoretical and numerical evidence that QML models exhibit further trainability issues not present in VQAs, arising from the use of a training dataset. We refer to these as dataset-induced barren plateaus. These results are most relevant when dealing with classical data, as here the choice of embedding scheme (i.e., the map between classical data and quantum states) can greatly affect the gradient scaling." @default.
• W4376609818 created "2023-05-17" @default.
• W4376609818 creator A5034327756 @default.
• W4376609818 creator A5065087289 @default.
• W4376609818 creator A5068470039 @default.
• W4376609818 creator A5074921335 @default.
• W4376609818 creator A5088973719 @default.
• W4376609818 date "2023-05-15" @default.
• W4376609818 modified "2023-10-14" @default.
• W4376609818 title "Subtleties in the trainability of quantum machine learning models" @default.
• W4376609818 cites W1970789124 @default.
• W4376609818 cites W1990514347 @default.
• W4376609818 cites W2016648670 @default.
• W4376609818 cites W2161685427 @default.
• W4376609818 cites W2559394418 @default.
• W4376609818 cites W2781738013 @default.
• W4376609818 cites W2790388700 @default.
• W4376609818 cites W2794444783 @default.
• W4376609818 cites W2796293949 @default.
• W4376609818 cites W2798434869 @default.
• W4376609818 cites W2811032035 @default.
• W4376609818 cites W2888228864 @default.
• W4376609818 cites W2896712926 @default.
• W4376609818 cites W2903221501 @default.
• W4376609818 cites W2905003072 @default.
• W4376609818 cites W2954369586 @default.
• W4376609818 cites W2972228381 @default.
• W4376609818 cites W3004965358 @default.
• W4376609818 cites W3009313620 @default.
• W4376609818 cites W3030829226 @default.
• W4376609818 cites W3090921460 @default.
• W4376609818 cites W3099514962 @default.
• W4376609818 cites W3100618339 @default.
• W4376609818 cites W3101678819 @default.
• W4376609818 cites W3104305016 @default.
• W4376609818 cites W3104599990 @default.
• W4376609818 cites W3111799909 @default.
• W4376609818 cites W3118800713 @default.
• W4376609818 cites W3119636101 @default.
• W4376609818 cites W3119774682 @default.
• W4376609818 cites W3125318774 @default.
• W4376609818 cites W3132743969 @default.
• W4376609818 cites W3136233239 @default.
• W4376609818 cites W3148001159 @default.
• W4376609818 cites W3149637861 @default.
• W4376609818 cites W3156188855 @default.
• W4376609818 cites W3158182757 @default.
• W4376609818 cites W3166275705 @default.
• W4376609818 cites W3169377977 @default.
• W4376609818 cites W3182433019 @default.
• W4376609818 cites W3183968998 @default.
• W4376609818 cites W3189250281 @default.
• W4376609818 cites W3193720999 @default.
• W4376609818 cites W3195630663 @default.
• W4376609818 cites W3204404766 @default.
• W4376609818 cites W3209107739 @default.
• W4376609818 cites W3211028885 @default.
• W4376609818 cites W3211718387 @default.
• W4376609818 cites W3215888540 @default.
• W4376609818 cites W4213235348 @default.
• W4376609818 cites W4214552167 @default.
• W4376609818 cites W4310898209 @default.
• W4376609818 cites W4312224136 @default.
• W4376609818 doi "https://doi.org/10.1007/s42484-023-00103-6" @default.
• W4376609818 hasPublicationYear "2023" @default.
• W4376609818 type Work @default.
• W4376609818 citedByCount "2" @default.
• W4376609818 countsByYear W43766098182023 @default.
• W4376609818 crossrefType "journal-article" @default.
• W4376609818 hasAuthorship W4376609818A5034327756 @default.
• W4376609818 hasAuthorship W4376609818A5065087289 @default.
• W4376609818 hasAuthorship W4376609818A5068470039 @default.
• W4376609818 hasAuthorship W4376609818A5074921335 @default.
• W4376609818 hasAuthorship W4376609818A5088973719 @default.
• W4376609818 hasBestOaLocation W43766098181 @default.
• W4376609818 hasConcept C111919701 @default.
• W4376609818 hasConcept C11413529 @default.
• W4376609818 hasConcept C119857082 @default.
• W4376609818 hasConcept C121332964 @default.
• W4376609818 hasConcept C121864883 @default.
• W4376609818 hasConcept C154945302 @default.
• W4376609818 hasConcept C202444582 @default.
• W4376609818 hasConcept C2524010 @default.
• W4376609818 hasConcept C2779094486 @default.
• W4376609818 hasConcept C33923547 @default.
• W4376609818 hasConcept C41008148 @default.
• W4376609818 hasConcept C41608201 @default.
• W4376609818 hasConcept C58053490 @default.
• W4376609818 hasConcept C62520636 @default.
• W4376609818 hasConcept C68339613 @default.
• W4376609818 hasConcept C84114770 @default.
• W4376609818 hasConcept C9652623 @default.
• W4376609818 hasConcept C99844830 @default.
• W4376609818 hasConceptScore W4376609818C111919701 @default.
• W4376609818 hasConceptScore W4376609818C11413529 @default.
• W4376609818 hasConceptScore W4376609818C119857082 @default.
• W4376609818 hasConceptScore W4376609818C121332964 @default.
• W4376609818 hasConceptScore W4376609818C121864883 @default.
• W4376609818 hasConceptScore W4376609818C154945302 @default.
• W4376609818 hasConceptScore W4376609818C202444582 @default.

• next