| Categorical reparameterization with gumbel-softmax E Jang, S Gu, B Poole arXiv preprint arXiv:1611.01144, 2016 | 2335 | 2016 |
| Adversarially learned inference V Dumoulin, I Belghazi, B Poole, O Mastropietro, A Lamb, M Arjovsky, ... arXiv preprint arXiv:1606.00704, 2016 | 1154 | 2016 |
| Continual learning through synaptic intelligence F Zenke, B Poole, S Ganguli International Conference on Machine Learning, 3987-3995, 2017 | 889 | 2017 |
| Unrolled generative adversarial networks L Metz, B Poole, D Pfau, J Sohl-Dickstein arXiv preprint arXiv:1611.02163, 2016 | 779 | 2016 |
| On the expressive power of deep neural networks M Raghu, B Poole, J Kleinberg, S Ganguli, J Sohl-Dickstein international conference on machine learning, 2847-2854, 2017 | 493 | 2017 |
| Exponential expressivity in deep neural networks through transient chaos B Poole, S Lahiri, M Raghu, J Sohl-Dickstein, S Ganguli Advances in Neural Information Processing Systems, 3504-3512, 2016 | 370 | 2016 |
| Fixing a Broken ELBO A Alemi, B Poole, I Fischer, J Dillon, RA Saurous, K Murphy International Conference on Machine Learning, 159-168, 2018 | 347* | 2018 |
| The Fast Bilateral Solver JT Barron, B Poole European Conference on Computer Vision, 617-632, 2016 | 280 | 2016 |
| On variational bounds of mutual information B Poole, S Ozair, A Van Den Oord, A Alemi, G Tucker International Conference on Machine Learning, 5171-5180, 2019 | 267* | 2019 |
| What makes for good views for contrastive learning? Y Tian, C Sun, B Poole, D Krishnan, C Schmid, P Isola arXiv preprint arXiv:2005.10243, 2020 | 217 | 2020 |
| Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods J Sohl-Dickstein, B Poole, S Ganguli | 110 | 2014 |
| Neuronal dynamics regulating brain and behavioral state transitions AS Andalman, VM Burns, M Lovett-Barron, M Broxton, B Poole, SJ Yang, ... Cell 177 (4), 970-985. e20, 2019 | 89 | 2019 |
| Analyzing noise in autoencoders and deep networks B Poole, J Sohl-Dickstein, S Ganguli arXiv preprint arXiv:1406.1831, 2014 | 85 | 2014 |
| Improving robustness without sacrificing accuracy with patch gaussian augmentation RG Lopes, D Yin, B Poole, J Gilmer, ED Cubuk arXiv preprint arXiv:1906.02611, 2019 | 82 | 2019 |
| Preventing posterior collapse with delta-vaes A Razavi, A Oord, B Poole, O Vinyals arXiv preprint arXiv:1901.03416, 2019 | 82 | 2019 |
| Score-based generative modeling through stochastic differential equations Y Song, J Sohl-Dickstein, DP Kingma, A Kumar, S Ermon, B Poole arXiv preprint arXiv:2011.13456, 2020 | 72 | 2020 |
| Direction selectivity in Drosophila emerges from preferred-direction enhancement and null-direction suppression JCS Leong, JJ Esch, B Poole, S Ganguli, TR Clandinin Journal of Neuroscience 36 (31), 8078-8092, 2016 | 66 | 2016 |
| Categorical reparametrization with gumble-softmax E Jang, S Gu, B Poole International Conference on Learning Representations (ICLR 2017), 2017 | 60 | 2017 |
| Weakly-supervised disentanglement without compromises F Locatello, B Poole, G Rätsch, B Schölkopf, O Bachem, M Tschannen International Conference on Machine Learning, 6348-6359, 2020 | 56 | 2020 |
| Discrete flows: Invertible generative models of discrete data D Tran, K Vafa, K Agrawal, L Dinh, B Poole Advances in Neural Information Processing Systems 32, 14719-14728, 2019 | 56 | 2019 |
Jascha Sohl-DicksteinGoogle BrainVerified email at google.com
