Matches in SemOpenAlex for { <https://semopenalex.org/work/W2809528734> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2809528734 abstract "Kernel methods are powerful supervised machine learning models for their strong generalization ability, especially on limited data to effectively generalize on unseen data. However, most kernel methods, including the state-of-the-art LIBSVM, are vulnerable to the curse of kernelization, making them infeasible to apply to large-scale datasets. This issue is exacerbated when kernel methods are used in conjunction with a grid search to tune their kernel parameters and hyperparameters which brings in the question of model robustness when applied to real datasets. In this paper, we propose a robust Bayesian Kernel Machine (BKM) - a Bayesian kernel machine that exploits the strengths of both the Bayesian modelling and kernel methods. A key challenge for such a formulation is the need for an efficient learning algorithm. To this end, we successfully extended the recent Stein variational theory for Bayesian inference for our proposed model, resulting in fast and efficient learning and prediction algorithms. Importantly our proposed BKM is resilient to the curse of kernelization, hence making it applicable to large-scale datasets and robust to parameter tuning, avoiding the associated expense and potential pitfalls with current practice of parameter tuning. Our extensive experimental results on 12 benchmark datasets show that our BKM without tuning any parameter can achieve comparable predictive performance with the state-of-the-art LIBSVM and significantly outperforms other baselines, while obtaining significantly speedup in terms of the total training time compared with its rivals" @default.
- W2809528734 created "2018-06-29" @default.
- W2809528734 creator A5011986638 @default.
- W2809528734 creator A5030891256 @default.
- W2809528734 creator A5035331823 @default.
- W2809528734 creator A5036447132 @default.
- W2809528734 creator A5086752305 @default.
- W2809528734 date "2018-07-19" @default.
- W2809528734 modified "2023-09-23" @default.
- W2809528734 title "Robust Bayesian Kernel Machine via Stein Variational Gradient Descent for Big Data" @default.
- W2809528734 cites W1510153068 @default.
- W2809528734 cites W1648445109 @default.
- W2809528734 cites W2114102615 @default.
- W2809528734 cites W2119821739 @default.
- W2809528734 cites W2124022122 @default.
- W2809528734 cites W2153635508 @default.
- W2809528734 cites W2158001550 @default.
- W2809528734 cites W2997980557 @default.
- W2809528734 cites W3004387475 @default.
- W2809528734 cites W3004533406 @default.
- W2809528734 doi "https://doi.org/10.1145/3219819.3220015" @default.
- W2809528734 hasPublicationYear "2018" @default.
- W2809528734 type Work @default.
- W2809528734 sameAs 2809528734 @default.
- W2809528734 citedByCount "4" @default.
- W2809528734 countsByYear W28095287342019 @default.
- W2809528734 countsByYear W28095287342020 @default.
- W2809528734 countsByYear W28095287342022 @default.
- W2809528734 crossrefType "proceedings-article" @default.
- W2809528734 hasAuthorship W2809528734A5011986638 @default.
- W2809528734 hasAuthorship W2809528734A5030891256 @default.
- W2809528734 hasAuthorship W2809528734A5035331823 @default.
- W2809528734 hasAuthorship W2809528734A5036447132 @default.
- W2809528734 hasAuthorship W2809528734A5086752305 @default.
- W2809528734 hasConcept C104317684 @default.
- W2809528734 hasConcept C107673813 @default.
- W2809528734 hasConcept C11413529 @default.
- W2809528734 hasConcept C114614502 @default.
- W2809528734 hasConcept C119857082 @default.
- W2809528734 hasConcept C13280743 @default.
- W2809528734 hasConcept C154945302 @default.
- W2809528734 hasConcept C160234255 @default.
- W2809528734 hasConcept C165464430 @default.
- W2809528734 hasConcept C185592680 @default.
- W2809528734 hasConcept C185798385 @default.
- W2809528734 hasConcept C205649164 @default.
- W2809528734 hasConcept C207225210 @default.
- W2809528734 hasConcept C33923547 @default.
- W2809528734 hasConcept C41008148 @default.
- W2809528734 hasConcept C55493867 @default.
- W2809528734 hasConcept C63479239 @default.
- W2809528734 hasConcept C74193536 @default.
- W2809528734 hasConcept C8642999 @default.
- W2809528734 hasConceptScore W2809528734C104317684 @default.
- W2809528734 hasConceptScore W2809528734C107673813 @default.
- W2809528734 hasConceptScore W2809528734C11413529 @default.
- W2809528734 hasConceptScore W2809528734C114614502 @default.
- W2809528734 hasConceptScore W2809528734C119857082 @default.
- W2809528734 hasConceptScore W2809528734C13280743 @default.
- W2809528734 hasConceptScore W2809528734C154945302 @default.
- W2809528734 hasConceptScore W2809528734C160234255 @default.
- W2809528734 hasConceptScore W2809528734C165464430 @default.
- W2809528734 hasConceptScore W2809528734C185592680 @default.
- W2809528734 hasConceptScore W2809528734C185798385 @default.
- W2809528734 hasConceptScore W2809528734C205649164 @default.
- W2809528734 hasConceptScore W2809528734C207225210 @default.
- W2809528734 hasConceptScore W2809528734C33923547 @default.
- W2809528734 hasConceptScore W2809528734C41008148 @default.
- W2809528734 hasConceptScore W2809528734C55493867 @default.
- W2809528734 hasConceptScore W2809528734C63479239 @default.
- W2809528734 hasConceptScore W2809528734C74193536 @default.
- W2809528734 hasConceptScore W2809528734C8642999 @default.
- W2809528734 hasLocation W28095287341 @default.
- W2809528734 hasOpenAccess W2809528734 @default.
- W2809528734 hasPrimaryLocation W28095287341 @default.
- W2809528734 hasRelatedWork W3081580854 @default.
- W2809528734 hasRelatedWork W3199608561 @default.
- W2809528734 hasRelatedWork W4210794429 @default.
- W2809528734 hasRelatedWork W4223456145 @default.
- W2809528734 hasRelatedWork W4283697347 @default.
- W2809528734 hasRelatedWork W4287683259 @default.
- W2809528734 hasRelatedWork W4295309597 @default.
- W2809528734 hasRelatedWork W4295681619 @default.
- W2809528734 hasRelatedWork W4309113015 @default.
- W2809528734 hasRelatedWork W4323894855 @default.
- W2809528734 isParatext "false" @default.
- W2809528734 isRetracted "false" @default.
- W2809528734 magId "2809528734" @default.
- W2809528734 workType "article" @default.