Matches in SemOpenAlex for { <https://semopenalex.org/work/W3166028936> ?p ?o ?g. }
- W3166028936 abstract "We introduce a method based on deep metric learning to perform Bayesian optimisation over high-dimensional, structured input spaces using variational autoencoders (VAEs). By extending ideas from supervised deep metric learning, we address a longstanding problem in high-dimensional VAE Bayesian optimisation, namely how to enforce a discriminative latent space as an inductive bias. Importantly, we achieve such an inductive bias using just 1% of the available labelled data relative to previous work, highlighting the sample efficiency of our approach. As a theoretical contribution, we present a proof of vanishing regret for our method. As an empirical contribution, we present state-of-the-art results on real-world high-dimensional black-box optimisation problems including property-guided molecule generation. It is the hope that the results presented in this paper can act as a guiding principle for realising effective high-dimensional Bayesian optimisation." @default.
- W3166028936 created "2021-06-22" @default.
- W3166028936 creator A5000651751 @default.
- W3166028936 creator A5012157944 @default.
- W3166028936 creator A5018539132 @default.
- W3166028936 creator A5027297585 @default.
- W3166028936 creator A5042241049 @default.
- W3166028936 creator A5047868177 @default.
- W3166028936 creator A5059324399 @default.
- W3166028936 creator A5062912204 @default.
- W3166028936 creator A5071367253 @default.
- W3166028936 creator A5072881452 @default.
- W3166028936 creator A5076411825 @default.
- W3166028936 creator A5086142353 @default.
- W3166028936 date "2021-06-07" @default.
- W3166028936 modified "2023-09-27" @default.
- W3166028936 title "High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning." @default.
- W3166028936 cites W137285897 @default.
- W3166028936 cites W1480330138 @default.
- W3166028936 cites W1510052597 @default.
- W3166028936 cites W1529817821 @default.
- W3166028936 cites W1638753340 @default.
- W3166028936 cites W170098597 @default.
- W3166028936 cites W1757990252 @default.
- W3166028936 cites W1898424075 @default.
- W3166028936 cites W1959608418 @default.
- W3166028936 cites W1968172834 @default.
- W3166028936 cites W1991908933 @default.
- W3166028936 cites W2001619934 @default.
- W3166028936 cites W2004834787 @default.
- W3166028936 cites W2012495032 @default.
- W3166028936 cites W2015563892 @default.
- W3166028936 cites W2093279820 @default.
- W3166028936 cites W2099201756 @default.
- W3166028936 cites W2104752854 @default.
- W3166028936 cites W2106053110 @default.
- W3166028936 cites W2110654099 @default.
- W3166028936 cites W2110798204 @default.
- W3166028936 cites W2117154949 @default.
- W3166028936 cites W2120405375 @default.
- W3166028936 cites W2135306627 @default.
- W3166028936 cites W2136261952 @default.
- W3166028936 cites W2138621090 @default.
- W3166028936 cites W2140376886 @default.
- W3166028936 cites W2144935315 @default.
- W3166028936 cites W2148694408 @default.
- W3166028936 cites W2149824585 @default.
- W3166028936 cites W2150796457 @default.
- W3166028936 cites W2192203593 @default.
- W3166028936 cites W2396901573 @default.
- W3166028936 cites W2526781987 @default.
- W3166028936 cites W2555454054 @default.
- W3166028936 cites W2622730215 @default.
- W3166028936 cites W2696385650 @default.
- W3166028936 cites W2757408183 @default.
- W3166028936 cites W2772936956 @default.
- W3166028936 cites W2785968631 @default.
- W3166028936 cites W2788268637 @default.
- W3166028936 cites W2803296075 @default.
- W3166028936 cites W2803435037 @default.
- W3166028936 cites W2809657535 @default.
- W3166028936 cites W2873705236 @default.
- W3166028936 cites W2888436131 @default.
- W3166028936 cites W2890019192 @default.
- W3166028936 cites W2895347732 @default.
- W3166028936 cites W2901371227 @default.
- W3166028936 cites W2902046464 @default.
- W3166028936 cites W2944213978 @default.
- W3166028936 cites W2946251732 @default.
- W3166028936 cites W2946928580 @default.
- W3166028936 cites W2951665052 @default.
- W3166028936 cites W2953308237 @default.
- W3166028936 cites W2962750597 @default.
- W3166028936 cites W2962753844 @default.
- W3166028936 cites W2962824535 @default.
- W3166028936 cites W2963263909 @default.
- W3166028936 cites W2963423218 @default.
- W3166028936 cites W2963659022 @default.
- W3166028936 cites W2963676163 @default.
- W3166028936 cites W2963775347 @default.
- W3166028936 cites W2963819570 @default.
- W3166028936 cites W2963988212 @default.
- W3166028936 cites W2964135722 @default.
- W3166028936 cites W2964265616 @default.
- W3166028936 cites W2964273603 @default.
- W3166028936 cites W2964308928 @default.
- W3166028936 cites W2966305713 @default.
- W3166028936 cites W2969999645 @default.
- W3166028936 cites W2972608701 @default.
- W3166028936 cites W2980498459 @default.
- W3166028936 cites W2983925976 @default.
- W3166028936 cites W2985931096 @default.
- W3166028936 cites W3023371261 @default.
- W3166028936 cites W3024236153 @default.
- W3166028936 cites W3026732421 @default.
- W3166028936 cites W3032441311 @default.
- W3166028936 cites W3034202663 @default.
- W3166028936 cites W3035250981 @default.
- W3166028936 cites W3036185205 @default.
- W3166028936 cites W3037589106 @default.