FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205430073> ?p ?o ?g. }

• W3205430073 abstract "We introduce the algorithm Bayesian Optimization (BO) with Fictitious Play (BOFiP) for the optimization of high dimensional black box functions. BOFiP decomposes the original, high dimensional, space into several sub-spaces defined by non-overlapping sets of dimensions. These sets are randomly generated at the start of the algorithm, and they form a partition of the dimensions of the original space. BOFiP searches the original space with alternating BO, within sub-spaces, and information exchange among sub-spaces, to update the sub-space function evaluation. The basic idea is to distribute the high dimensional optimization across low dimensional sub-spaces, where each sub-space is a player in an equal interest game. At each iteration, BO produces approximate best replies that update the players belief distribution. The belief update and BO alternate until a stopping condition is met. High dimensional problems are common in real applications, and several contributions in the BO literature have highlighted the difficulty in scaling to high dimensions due to the computational complexity associated to the estimation of the model hyperparameters. Such complexity is exponential in the problem dimension, resulting in substantial loss of performance for most techniques with the increase of the input dimensionality. We compare BOFiP to several state-of-the-art approaches in the field of high dimensional black box optimization. The numerical experiments show the performance over three benchmark objective functions from 20 up to 1000 dimensions. A neural network architecture design problem is tested with 42 up to 911 nodes in 6 up to 92 layers, respectively, resulting into networks with 500 up to 10,000 weights. These sets of experiments empirically show that BOFiP outperforms its competitors, showing consistent performance across different problems and increasing problem dimensionality." @default.
• W3205430073 created "2021-10-25" @default.
• W3205430073 creator A5030795316 @default.
• W3205430073 creator A5049158387 @default.
• W3205430073 creator A5088969714 @default.
• W3205430073 date "2021-10-07" @default.
• W3205430073 modified "2023-09-27" @default.
• W3205430073 title "Scaling Bayesian Optimization With Game Theory." @default.
• W3205430073 cites W1480330138 @default.
• W3205430073 cites W1484867920 @default.
• W3205430073 cites W1510052597 @default.
• W3205430073 cites W1529817821 @default.
• W3205430073 cites W1580216809 @default.
• W3205430073 cites W1871676304 @default.
• W3205430073 cites W1915824153 @default.
• W3205430073 cites W1971021761 @default.
• W3205430073 cites W1988945200 @default.
• W3205430073 cites W2018044188 @default.
• W3205430073 cites W2023362591 @default.
• W3205430073 cites W2055537715 @default.
• W3205430073 cites W2063180182 @default.
• W3205430073 cites W2064076655 @default.
• W3205430073 cites W2084812512 @default.
• W3205430073 cites W2090965439 @default.
• W3205430073 cites W2096649264 @default.
• W3205430073 cites W2097998348 @default.
• W3205430073 cites W2099201756 @default.
• W3205430073 cites W2106411961 @default.
• W3205430073 cites W2106861182 @default.
• W3205430073 cites W2108114251 @default.
• W3205430073 cites W2118247617 @default.
• W3205430073 cites W2129887565 @default.
• W3205430073 cites W2131241448 @default.
• W3205430073 cites W2133778423 @default.
• W3205430073 cites W2136047985 @default.
• W3205430073 cites W2149254401 @default.
• W3205430073 cites W2151604161 @default.
• W3205430073 cites W2156375221 @default.
• W3205430073 cites W2162737890 @default.
• W3205430073 cites W2164598857 @default.
• W3205430073 cites W2164923190 @default.
• W3205430073 cites W2171890636 @default.
• W3205430073 cites W2192203593 @default.
• W3205430073 cites W2372373432 @default.
• W3205430073 cites W2402456051 @default.
• W3205430073 cites W2467817358 @default.
• W3205430073 cites W2547615080 @default.
• W3205430073 cites W2553055651 @default.
• W3205430073 cites W2553755808 @default.
• W3205430073 cites W2573774999 @default.
• W3205430073 cites W2622730215 @default.
• W3205430073 cites W2736684539 @default.
• W3205430073 cites W2740683467 @default.
• W3205430073 cites W2787689390 @default.
• W3205430073 cites W2788642651 @default.
• W3205430073 cites W2873705236 @default.
• W3205430073 cites W2890055393 @default.
• W3205430073 cites W2893281241 @default.
• W3205430073 cites W2901378281 @default.
• W3205430073 cites W2914275007 @default.
• W3205430073 cites W2945677399 @default.
• W3205430073 cites W2952677397 @default.
• W3205430073 cites W2953083211 @default.
• W3205430073 cites W2955908957 @default.
• W3205430073 cites W2962753844 @default.
• W3205430073 cites W2963330446 @default.
• W3205430073 cites W2963659022 @default.
• W3205430073 cites W2963674301 @default.
• W3205430073 cites W2964056475 @default.
• W3205430073 cites W2964343907 @default.
• W3205430073 cites W2966753957 @default.
• W3205430073 cites W2980498459 @default.
• W3205430073 cites W2998235384 @default.
• W3205430073 cites W3006988978 @default.
• W3205430073 cites W3013369344 @default.
• W3205430073 cites W3035373510 @default.
• W3205430073 cites W3148958427 @default.
• W3205430073 cites W84569508 @default.
• W3205430073 hasPublicationYear "2021" @default.
• W3205430073 type Work @default.
• W3205430073 sameAs 3205430073 @default.
• W3205430073 citedByCount "0" @default.
• W3205430073 crossrefType "posted-content" @default.
• W3205430073 hasAuthorship W3205430073A5030795316 @default.
• W3205430073 hasAuthorship W3205430073A5049158387 @default.
• W3205430073 hasAuthorship W3205430073A5088969714 @default.
• W3205430073 hasConcept C111030470 @default.
• W3205430073 hasConcept C11413529 @default.
• W3205430073 hasConcept C114614502 @default.
• W3205430073 hasConcept C126255220 @default.
• W3205430073 hasConcept C13280743 @default.
• W3205430073 hasConcept C137836250 @default.
• W3205430073 hasConcept C154945302 @default.
• W3205430073 hasConcept C185798385 @default.
• W3205430073 hasConcept C205649164 @default.
• W3205430073 hasConcept C2524010 @default.
• W3205430073 hasConcept C2778049539 @default.
• W3205430073 hasConcept C33676613 @default.
• W3205430073 hasConcept C33923547 @default.
• W3205430073 hasConcept C41008148 @default.

• next