Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890340748> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2890340748 abstract "Black box discrete optimization (BBDO) appears in wide range of engineering tasks. Evolutionary or other BBDO approaches have been applied, aiming at automating necessary tuning of system parameters, such as hyper parameter tuning of machine learning based systems when being installed for a specific task. However, automation is often jeopardized by the need of strategy parameter tuning for BBDO algorithms. An expert with the domain knowledge must undergo time-consuming strategy parameter tuning. This paper proposes a parameterless BBDO algorithm based on information geometric optimization, a recent framework for black box optimization using stochastic natural gradient. Inspired by some theoretical implications, we develop an adaptation mechanism for strategy parameters of the stochastic natural gradient method for discrete search domains. The proposed algorithm is evaluated on commonly used test problems. It is further extended to two examples of simultaneous optimization of the hyper parameters and the connection weights of deep learning models, leading to a faster optimization than the existing approaches without any effort of parameter tuning." @default.
- W2890340748 created "2018-09-27" @default.
- W2890340748 creator A5005268349 @default.
- W2890340748 creator A5030905304 @default.
- W2890340748 creator A5036763177 @default.
- W2890340748 creator A5038757231 @default.
- W2890340748 creator A5078648227 @default.
- W2890340748 date "2018-09-17" @default.
- W2890340748 modified "2023-09-24" @default.
- W2890340748 title "Parameterless Stochastic Natural Gradient Method for Discrete Optimization and its Application to Hyper-Parameter Optimization for Neural Network" @default.
- W2890340748 cites W104184427 @default.
- W2890340748 cites W1480347379 @default.
- W2890340748 cites W1566710167 @default.
- W2890340748 cites W1990799344 @default.
- W2890340748 cites W2034813183 @default.
- W2890340748 cites W2142027531 @default.
- W2890340748 cites W2148379945 @default.
- W2890340748 cites W2162036626 @default.
- W2890340748 cites W2194775991 @default.
- W2890340748 cites W2553303224 @default.
- W2890340748 cites W2784822746 @default.
- W2890340748 cites W2886000387 @default.
- W2890340748 cites W2950182411 @default.
- W2890340748 cites W2950714608 @default.
- W2890340748 cites W2962746461 @default.
- W2890340748 cites W2962835968 @default.
- W2890340748 cites W2963055657 @default.
- W2890340748 cites W2963446712 @default.
- W2890340748 cites W594357522 @default.
- W2890340748 cites W7934506 @default.
- W2890340748 cites W2084690464 @default.
- W2890340748 doi "https://doi.org/10.48550/arxiv.1809.06517" @default.
- W2890340748 hasPublicationYear "2018" @default.
- W2890340748 type Work @default.
- W2890340748 sameAs 2890340748 @default.
- W2890340748 citedByCount "0" @default.
- W2890340748 crossrefType "posted-content" @default.
- W2890340748 hasAuthorship W2890340748A5005268349 @default.
- W2890340748 hasAuthorship W2890340748A5030905304 @default.
- W2890340748 hasAuthorship W2890340748A5036763177 @default.
- W2890340748 hasAuthorship W2890340748A5038757231 @default.
- W2890340748 hasAuthorship W2890340748A5078648227 @default.
- W2890340748 hasBestOaLocation W28903407481 @default.
- W2890340748 hasConcept C109578324 @default.
- W2890340748 hasConcept C11413529 @default.
- W2890340748 hasConcept C119857082 @default.
- W2890340748 hasConcept C122357587 @default.
- W2890340748 hasConcept C126255220 @default.
- W2890340748 hasConcept C127413603 @default.
- W2890340748 hasConcept C137836250 @default.
- W2890340748 hasConcept C146978453 @default.
- W2890340748 hasConcept C154945302 @default.
- W2890340748 hasConcept C194387892 @default.
- W2890340748 hasConcept C204323151 @default.
- W2890340748 hasConcept C33923547 @default.
- W2890340748 hasConcept C41008148 @default.
- W2890340748 hasConcept C50644808 @default.
- W2890340748 hasConcept C92995354 @default.
- W2890340748 hasConcept C94966114 @default.
- W2890340748 hasConceptScore W2890340748C109578324 @default.
- W2890340748 hasConceptScore W2890340748C11413529 @default.
- W2890340748 hasConceptScore W2890340748C119857082 @default.
- W2890340748 hasConceptScore W2890340748C122357587 @default.
- W2890340748 hasConceptScore W2890340748C126255220 @default.
- W2890340748 hasConceptScore W2890340748C127413603 @default.
- W2890340748 hasConceptScore W2890340748C137836250 @default.
- W2890340748 hasConceptScore W2890340748C146978453 @default.
- W2890340748 hasConceptScore W2890340748C154945302 @default.
- W2890340748 hasConceptScore W2890340748C194387892 @default.
- W2890340748 hasConceptScore W2890340748C204323151 @default.
- W2890340748 hasConceptScore W2890340748C33923547 @default.
- W2890340748 hasConceptScore W2890340748C41008148 @default.
- W2890340748 hasConceptScore W2890340748C50644808 @default.
- W2890340748 hasConceptScore W2890340748C92995354 @default.
- W2890340748 hasConceptScore W2890340748C94966114 @default.
- W2890340748 hasLocation W28903407481 @default.
- W2890340748 hasOpenAccess W2890340748 @default.
- W2890340748 hasPrimaryLocation W28903407481 @default.
- W2890340748 hasRelatedWork W1626279227 @default.
- W2890340748 hasRelatedWork W1968947297 @default.
- W2890340748 hasRelatedWork W1991366585 @default.
- W2890340748 hasRelatedWork W1991617942 @default.
- W2890340748 hasRelatedWork W2062144119 @default.
- W2890340748 hasRelatedWork W2151065257 @default.
- W2890340748 hasRelatedWork W2785308959 @default.
- W2890340748 hasRelatedWork W2913526350 @default.
- W2890340748 hasRelatedWork W3099810946 @default.
- W2890340748 hasRelatedWork W2124446612 @default.
- W2890340748 isParatext "false" @default.
- W2890340748 isRetracted "false" @default.
- W2890340748 magId "2890340748" @default.
- W2890340748 workType "article" @default.