Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules.
20181.1k citationsDavid Duvenaud, Ryan P. Adams et al.profile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
Countries citing papers authored by David Duvenaud
Since
Specialization
Citations
This map shows the geographic impact of David Duvenaud's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by David Duvenaud with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites David Duvenaud more than expected).
This network shows the impact of papers produced by David Duvenaud. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by David Duvenaud. The network helps show where David Duvenaud may publish in the future.
Co-authorship network of co-authors of David Duvenaud
This figure shows the co-authorship network connecting the top 25 collaborators of David Duvenaud.
A scholar is included among the top collaborators of David Duvenaud based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with David Duvenaud. David Duvenaud is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Li, Xuechen, Ting‐Kam Leonard Wong, Ricky T. Q. Chen, & David Duvenaud. (2020). Scalable Gradients for Stochastic Differential Equations. International Conference on Artificial Intelligence and Statistics. 3870–3882.5 indexed citations
2.
Grathwohl, Will, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, & Richard S. Zemel. (2020). Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling. International Conference on Machine Learning. 1. 3732–3747.3 indexed citations
3.
Tonekaboni, Sana, Shalmali Joshi, Kieran R. Campbell, David Duvenaud, & Anna Goldenberg. (2020). What went wrong and when? Instance-wise feature importance for time-series black-box models. Neural Information Processing Systems. 33. 799–809.14 indexed citations
4.
Bettencourt, Jesse, et al.. (2020). Learning Differential Equations that are Easy to Solve. arXiv (Cornell University). 33. 4370–4380.4 indexed citations
5.
Grathwohl, Will, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, & Richard S. Zemel. (2020). Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling. arXiv (Cornell University).1 indexed citations
6.
Chen, Ricky T. Q., Jens Behrmann, David Duvenaud, & Joern-Henrik Jacobsen. (2019). Residual Flows for Invertible Generative Modeling. Neural Information Processing Systems. 32. 9916–9926.18 indexed citations
7.
Rubanova, Yulia, Ricky T. Q. Chen, & David Duvenaud. (2019). Latent Ordinary Differential Equations for Irregularly-Sampled Time Series. Neural Information Processing Systems. 32. 5320–5330.120 indexed citations
Behrmann, Jens, Will Grathwohl, Ricky T. Q. Chen, David Duvenaud, & Joern-Henrik Jacobsen. (2019). Invertible Residual Networks. International Conference on Machine Learning. 573–582.40 indexed citations
10.
Chang, Chun‐Hao, Elliot Creager, Anna Goldenberg, & David Duvenaud. (2018). Explaining Image Classifiers by Adaptive Dropout and Generative In-filling.. arXiv (Cornell University).2 indexed citations
11.
Li, Xuechen, et al.. (2018). Isolating Sources of Disentanglement in Variational Autoencoders.. International Conference on Learning Representations.15 indexed citations
12.
Nado, Zachary, et al.. (2018). STOCHASTIC GRADIENT LANGEVIN DYNAMICS THAT EXPLOIT NEURAL NETWORK STRUCTURE. International Conference on Learning Representations.4 indexed citations
13.
Wu, Yuhuai, et al.. (2017). Sticking the Landing: An Asymptotically Zero-Variance Gradient Estimator for Variational Inference.. arXiv (Cornell University).2 indexed citations
14.
Morris, Quaid, et al.. (2017). Reinterpreting Importance-Weighted Autoencoders. International Conference on Learning Representations.8 indexed citations
15.
Johnson, Matthew, David Duvenaud, Alexander B. Wiltschko, Ryan P. Adams, & Sandeep Robert Datta. (2016). Composing graphical models with neural networks for structured representations and fast inference. Neural Information Processing Systems. 29. 2946–2954.58 indexed citations
16.
Schulz, Eric, Joshua B. Tenenbaum, David Duvenaud, Maarten Speekenbrink, & Samuel J. Gershman. (2016). Probing the Compositionality of Intuitive Functions. DSpace@MIT (Massachusetts Institute of Technology). 29. 3729–3737.7 indexed citations
17.
Johnson, Matthew, David Duvenaud, Alexander B. Wiltschko, Sandeep Robert Datta, & Ryan P. Adams. (2016). Structured VAEs: Composing Probabilistic Graphical Models and Variational Autoencoders. arXiv (Cornell University).8 indexed citations
18.
Duvenaud, David, Dougal Maclaurin, & Ryan P. Adams. (2016). Early Stopping as Nonparametric Variational Inference. International Conference on Artificial Intelligence and Statistics. 1070–1077.21 indexed citations
19.
Osborne, Michael A., Roman Garnett, Zoubin Ghahramani, et al.. (2012). Active Learning of Model Evidence Using Bayesian Quadrature. Cambridge University Engineering Department Publications Database. 25. 46–54.24 indexed citations
20.
Duvenaud, David, Daniel Eaton, Kevin P. Murphy, & Mark Schmidt. (2008). Causal learning without DAGs. Neural Information Processing Systems. 177–190.4 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.