| Tree boosting with xgboost-why does xgboost win" every" machine learning competition? D Nielsen NTNU, 2016 | 478* | 2016 |
| Argmax flows and multinomial diffusion: Learning categorical distributions E Hoogeboom, D Nielsen, P Jaini, P Forré, M Welling Advances in Neural Information Processing Systems 34, 12454-12465, 2021 | 294* | 2021 |
| Fast and scalable bayesian deep learning by weight-perturbation in adam M Khan, D Nielsen, V Tangkaratt, W Lin, Y Gal, A Srivastava International conference on machine learning, 2611-2620, 2018 | 278 | 2018 |
| Survae flows: Surjections to bridge the gap between vaes and flows D Nielsen, P Jaini, E Hoogeboom, O Winther, M Welling Advances in Neural Information Processing Systems 33, 12685-12696, 2020 | 98 | 2020 |
| Diffusion models for video prediction and infilling T Höppe, A Mehrjou, S Bauer, D Nielsen, A Dittadi arXiv preprint arXiv:2206.07696, 2022 | 74 | 2022 |
| Slang: Fast structured covariance approximations for bayesian deep learning with natural gradient A Mishkin, F Kunstner, D Nielsen, M Schmidt, ME Khan Advances in neural information processing systems 31, 2018 | 67 | 2018 |
| Fast yet simple natural-gradient descent for variational inference in complex models ME Khan, D Nielsen 2018 International Symposium on Information Theory and Its Applications …, 2018 | 58 | 2018 |
| Few-shot diffusion models G Giannone, D Nielsen, O Winther arXiv preprint arXiv:2205.15463, 2022 | 36 | 2022 |
| Variational adaptive-Newton method for explorative learning ME Khan, W Lin, V Tangkaratt, Z Liu, D Nielsen arXiv preprint arXiv:1711.05560, 2017 | 17 | 2017 |
| Closing the dequantization gap: Pixelcnn as a single-layer flow D Nielsen, O Winther Advances in Neural Information Processing Systems 33, 3724-3734, 2020 | 16 | 2020 |
| Sampling in combinatorial spaces with survae flow augmented mcmc P Jaini, D Nielsen, M Welling International Conference on Artificial Intelligence and Statistics, 3349-3357, 2021 | 10 | 2021 |
| Argmax flows: Learning categorical distributions with normalizing flows E Hoogeboom, D Nielsen, P Jaini, P Forré, M Welling Third Symposium on Advances in Approximate Bayesian Inference, 2020 | 4 | 2020 |
| Natural-gradient stochastic variational inference for non-conjugate structured variational autoencoder W Lin, ME Khan, N Hubacher, D Nielsen International Conference on Machine Learning, 2017 | 2 | 2017 |
| Image classifier comprising a non-injective transformation D Nielsen, E Hoogeboom, K Sakmann, M Welling, P Jaini US Patent App. 17/345,702, 2022 | 1 | 2022 |
| PixelCNN as a Single-Layer Flow D Nielsen, O Winther NeurIPS 2019 Workshop on Bayesian Deep Learning, 2019 | 1 | 2019 |
| The Variational Adaptive-Newton Method ME Khan, W Lin, V Tangkaratt, Z Liu, D Nielsen NeurIPS Workshop on Advances in Approximate Bayesian Inference, 2017 | 1 | 2017 |
| Image generation model based on log-likelihood E Hoogeboom, D Nielsen, M Welling, P Forre, P Jaini, WH Beluch US Patent App. 17/445,891, 2022 | | 2022 |
| Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions P Forre, E Hoogeboom, P Jaini, D Nielsen, M Welling 15San Diego, CANeural Information Processing Systems Foundation, 2022 | | 2022 |
| Deep Generative Flows with Non-Bijective Layers D Nielsen Technical University of Denmark, 2022 | | 2022 |
