SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient. Aaron Mishkin, Frederik Kunstner, Didrik Nielsen, Mark Schmidt, Mohammad Emtiyaz Khan. In Conference on Neural Information Processing Systems (NIPS), 2018.
Fast yet Simple Natural-Gradient Descent for Variational Inference in Complex Models. Mohammad Emtiyaz Khan, Didrik Nielsen. In International Symposium on Information Theory and Its Applications (ISITA), 2018.
Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam. Mohammad Emtiyaz Khan, Didrik Nielsen, Voot Tangkaratt, Wu Lin, Yarin Gal, Akash Srivastava. In International Conference on Machine Learning (ICML), 2018.
- Variational Adaptive-Newton Method for Explorative Learning. Mohammad Emtiyaz Khan, Wu Lin, Voot Tangkaratt, Zuozhu Liu, Didrik Nielsen. On arXiv, 2017.
Variational Adaptive-Newton Method. Mohammad Emtiyaz Khan, Wu Lin, Voot Tangkaratt, Zuozhu Liu, Didrik Nielsen. In Workshop on Advances in Approximate Bayesian Inference, NIPS, 2017.
Natural-Gradient Stochastic Variational Inference for Non-Conjugate Structured Variational Autoencoder. Wu Lin, Mohammad Emtiyaz Khan, Nicolas Hubacher, Didrik Nielsen. In Workshop on Deep Structured Prediction, ICML, 2017.
- Tree Boosting With XGBoost - Why Does XGBoost Win “Every” Machine Learning Competition?. Didrik Nielsen. MSc Thesis, 2016.