| Convolutional Networks on Graphs for Learning Molecular Fingerprints D Duvenaud, D Maclaurin, J Aguilera-Iparraguirre, R Gómez-Bombarelli, ... Neural Information Processing Systems, 2015 | 2830 | 2015 |
| Neural Ordinary Differential Equations RTQ Chen, Y Rubanova, J Bettencourt, D Duvenaud Neural Information Processing Systems, 2018 | 2197 | 2018 |
| Automatic chemical design using a data-driven continuous representation of molecules R Gómez-Bombarelli, JN Wei, D Duvenaud, JM Hernández-Lobato, ... ACS central science 4 (2), 268-276, 2018 | 1849 | 2018 |
| Isolating sources of disentanglement in variational autoencoders RTQ Chen, X Li, R Grosse, D Duvenaud Neural Information Processing Systems, arXiv preprint arXiv:1802.04942, 2018 | 781 | 2018 |
| Gradient-based hyperparameter optimization through reversible learning D Maclaurin, D Duvenaud, R Adams International conference on machine learning, 2113-2122, 2015 | 688 | 2015 |
| Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach R Gómez-Bombarelli, J Aguilera-Iparraguirre, TD Hirzel, D Duvenaud, ... Nature materials 15 (10), 1120-1127, 2016 | 646 | 2016 |
| Automatic model construction with Gaussian processes D Duvenaud University of Cambridge, 2014 | 510 | 2014 |
| FFJORD: Free-form continuous dynamics for scalable reversible generative models W Grathwohl, RTQ Chen, J Betterncourt, I Sutskever, D Duvenaud International Conference on Learning Representations, 2018 | 507* | 2018 |
| Structure Discovery in Nonparametric Regression through Compositional Kernel Search D Duvenaud, JR Lloyd, R Grosse, JB Tenenbaum, Z Ghahramani International Conference on Machine Learning, 2013 | 481 | 2013 |
| Composing graphical models with neural networks for structured representations and fast inference MJ Johnson, DK Duvenaud, A Wiltschko, RP Adams, SR Datta Advances in neural information processing systems 29, 2016 | 470 | 2016 |
| Latent ODEs for irregularly-sampled time series Y Rubanova, RTQ Chen, D Duvenaud Neural Information Processing Systems, 2019 | 357* | 2019 |
| Invertible residual networks J Behrmann, W Grathwohl, RTQ Chen, D Duvenaud, JH Jacobsen International Conference on Machine Learning, 2018 | 345 | 2018 |
| Neural networks for the prediction of organic chemistry reactions JN Wei, D Duvenaud, A Aspuru-Guzik ACS central science 2 (10), 725-732, 2016 | 327 | 2016 |
| Additive Gaussian Processes D Duvenaud, H Nickisch, CE Rasmussen Neural Information Processing Systems, 2011 | 308 | 2011 |
| Autograd: Reverse-mode differentiation of native python D Maclaurin, D Duvenaud, M Johnson, RP Adams ICML workshop on Automatic Machine Learning, 2015 | 241* | 2015 |
| Automatic construction and natural-language description of nonparametric regression models JR Lloyd, D Duvenaud, R Grosse, JB Tenenbaum, Z Ghahramani Association for the Advancement of Artificial Intelligence, 2014 | 236 | 2014 |
| Backpropagation through the void: Optimizing control variates for black-box gradient estimation W Grathwohl, D Choi, Y Wu, G Roeder, D Duvenaud International Conference on Learning Representations, arXiv preprint arXiv …, 2017 | 229 | 2017 |
| Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One W Grathwohl, KC Wang, JH Jacobsen, D Duvenaud, M Norouzi, ... International Conference on Learning Representations 2020, 2019 | 228 | 2019 |
| Inference suboptimality in variational autoencoders C Cremer, X Li, D Duvenaud International Conference on Machine Learning, 1078-1086, 2018 | 204 | 2018 |
| Residual Flows for Invertible Generative Modeling RTQ Chen, J Behrmann, D Duvenaud, JH Jacobsen Neural Information Processing Systems, 2019 | 193 | 2019 |
Ryan P. AdamsPrinceton University在 princeton.edu 的电子邮件经过验证
