Florian Wenzel is an Applied Scientist at Amazon AWS AI and member of the Causal Representation Learning team in Tübingen. His research interests include reliable deep learning, robustness and causal representation learning. From 2019 - 2021, he was a postdoctoral researcher at Google Brain Berlin. He received his PhD in machine learning from Humboldt-Universität zu Berlin in 2019, working with his advisor Marius Kloft (TU Kaiserslautern and USC), Manfred Opper (TU Berlin) and Stephan Mandt (UCI).
PhD in Machine Learning, 2019
Humboldt-Universität zu Berlin and TU Kaiserslautern
MSc in Mathematics, 2015
Humboldt-Universität zu Berlin
In our NeurIPS paper, we leverage diversity stemming from models with different hyperparameters. This leads to SotA accuracy and more robust predictions. Hyper-deep ensembles expand on deep ensembles by integrating over a larger space of hyperparameters. Hyper-batch ensembles expand on efficient methods. Also check out the thread by Dustin Tran.
In our ICML 2020 paper, we tackle the question: How Good is the Bayes Posterior in Deep Neural Networks Really? We cast doubt on the current understanding of Bayes posteriors in popular deep neural networks. We find that using cold posteriors improves the performance of BNNs but sharply deviate from the Bayesian paradigm. We put forward several hypotheses that could explain cold posteriors and evaluate the hypotheses through experiments.
In our AISTATS paper, we propose a method that automatically transforms non-conjugate Gaussian process models into conjugate models. In the transformed model inference is easy, much faster and more stable. No more need for long manual derivations of complete conditional distributions and their expectations (although I enjoy them from time to time).
Great news: I started a postdoctoral researcher position at Google Brain Berlin. I’m excited to work on topics around Bayesian deep learning. Stay tuned! :-)
We have a new paper on augmentation variational inference, to appear at UAI 2019 in Tel Aviv. We consider Gaussian Process multi-class classification and propose a new multi-class likelihood which has two benefits: it leads to well-calibrated uncertainty estimates and allows for an efficient conditionally conjugate latent variable augmentation. The code can be found in our Julia GP package AugmentedGaussianProcesses.
This year at NeurIPS in Montreal, I have three workshop papers. Together with my colleagues, I will present at: