Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891359018> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2891359018 abstract "We introduce two quantum algorithms for solving structured prediction problems. We show that a stochastic subgradient descent method that uses the quantum minimum finding algorithm and takes its probabilistic failure into account solves the structured prediction problem with a runtime that scales with the square root of the size of the label space, and in $widetilde Oleft(1/epsilonright)$ with respect to the precision, $epsilon$, of the solution. Motivated by robust inference techniques in machine learning, we introduce another quantum algorithm that solves a smooth approximation of the structured prediction problem with a similar quantum speedup in the size of the label space and a similar scaling in the precision parameter. In doing so, we analyze a stochastic gradient algorithm for convex optimization in the presence of an additive error in the calculation of the gradients, and show that its convergence rate does not deteriorate if the additive errors are of the order $O(sqrtepsilon)$. This algorithm uses quantum Gibbs sampling at temperature $Omega (epsilon)$ as a subroutine. Based on these theoretical observations, we propose a method for using quantum Gibbs samplers to combine feedforward neural networks with probabilistic graphical models for quantum machine learning. Our numerical results using Monte Carlo simulations on an image tagging task demonstrate the benefit of the approach." @default.
- W2891359018 created "2018-09-27" @default.
- W2891359018 creator A5007451973 @default.
- W2891359018 creator A5011087859 @default.
- W2891359018 creator A5054518852 @default.
- W2891359018 creator A5083977271 @default.
- W2891359018 date "2018-09-11" @default.
- W2891359018 modified "2023-10-17" @default.
- W2891359018 title "Smooth Structured Prediction Using Quantum and Classical Gibbs Samplers" @default.
- W2891359018 hasPublicationYear "2018" @default.
- W2891359018 type Work @default.
- W2891359018 sameAs 2891359018 @default.
- W2891359018 citedByCount "0" @default.
- W2891359018 crossrefType "posted-content" @default.
- W2891359018 hasAuthorship W2891359018A5007451973 @default.
- W2891359018 hasAuthorship W2891359018A5011087859 @default.
- W2891359018 hasAuthorship W2891359018A5054518852 @default.
- W2891359018 hasAuthorship W2891359018A5083977271 @default.
- W2891359018 hasConcept C107673813 @default.
- W2891359018 hasConcept C111919701 @default.
- W2891359018 hasConcept C11413529 @default.
- W2891359018 hasConcept C121332964 @default.
- W2891359018 hasConcept C126255220 @default.
- W2891359018 hasConcept C137019171 @default.
- W2891359018 hasConcept C154945302 @default.
- W2891359018 hasConcept C158424031 @default.
- W2891359018 hasConcept C158968445 @default.
- W2891359018 hasConcept C2779094486 @default.
- W2891359018 hasConcept C28826006 @default.
- W2891359018 hasConcept C33923547 @default.
- W2891359018 hasConcept C41008148 @default.
- W2891359018 hasConcept C49937458 @default.
- W2891359018 hasConcept C62520636 @default.
- W2891359018 hasConcept C68339613 @default.
- W2891359018 hasConcept C84114770 @default.
- W2891359018 hasConceptScore W2891359018C107673813 @default.
- W2891359018 hasConceptScore W2891359018C111919701 @default.
- W2891359018 hasConceptScore W2891359018C11413529 @default.
- W2891359018 hasConceptScore W2891359018C121332964 @default.
- W2891359018 hasConceptScore W2891359018C126255220 @default.
- W2891359018 hasConceptScore W2891359018C137019171 @default.
- W2891359018 hasConceptScore W2891359018C154945302 @default.
- W2891359018 hasConceptScore W2891359018C158424031 @default.
- W2891359018 hasConceptScore W2891359018C158968445 @default.
- W2891359018 hasConceptScore W2891359018C2779094486 @default.
- W2891359018 hasConceptScore W2891359018C28826006 @default.
- W2891359018 hasConceptScore W2891359018C33923547 @default.
- W2891359018 hasConceptScore W2891359018C41008148 @default.
- W2891359018 hasConceptScore W2891359018C49937458 @default.
- W2891359018 hasConceptScore W2891359018C62520636 @default.
- W2891359018 hasConceptScore W2891359018C68339613 @default.
- W2891359018 hasConceptScore W2891359018C84114770 @default.
- W2891359018 hasLocation W28913590181 @default.
- W2891359018 hasOpenAccess W2891359018 @default.
- W2891359018 hasPrimaryLocation W28913590181 @default.
- W2891359018 hasRelatedWork W1975907901 @default.
- W2891359018 hasRelatedWork W2766294686 @default.
- W2891359018 hasRelatedWork W2766404040 @default.
- W2891359018 hasRelatedWork W2797767079 @default.
- W2891359018 hasRelatedWork W2806409822 @default.
- W2891359018 hasRelatedWork W2868872787 @default.
- W2891359018 hasRelatedWork W2898913178 @default.
- W2891359018 hasRelatedWork W2964327027 @default.
- W2891359018 hasRelatedWork W2968391660 @default.
- W2891359018 hasRelatedWork W2972442636 @default.
- W2891359018 hasRelatedWork W2982431570 @default.
- W2891359018 hasRelatedWork W2984601129 @default.
- W2891359018 hasRelatedWork W3017142254 @default.
- W2891359018 hasRelatedWork W3031497571 @default.
- W2891359018 hasRelatedWork W3036234777 @default.
- W2891359018 hasRelatedWork W3047467909 @default.
- W2891359018 hasRelatedWork W3182433019 @default.
- W2891359018 hasRelatedWork W3194650937 @default.
- W2891359018 hasRelatedWork W3197090376 @default.
- W2891359018 isParatext "false" @default.
- W2891359018 isRetracted "false" @default.
- W2891359018 magId "2891359018" @default.
- W2891359018 workType "article" @default.