Talks & organizing


21.1.2021Statistics as linear algebra – distribution embeddings and operators on reproducing kernel Hilbert spacesUniv. of Bristol (slides)
11.7.2019Kernel conditional density operatorsTU Berlin (slides)
16.8.2018Tutorial on modern kernel methodsZalando Research (slides)
28.6.2018Markov Chain Importance SamplingBTU Cottbus (slides)
30.5.2018Markov Chain Importance SamplingUniversität Mannheim (slides)
23.3.2018Highly efficient Bayesian inference with a novel estimator for Metropolis HastingsZalando Research (slides)
3.7.2017Stochastic gradient Metropolis-HastingsMonte Carlo Methods 2017
8.6.2017A highly efficient estimator for Markov Chain algorithmsBayes in Paris, ENSAE
8.3.2017A Bayesian model for sparse structured sequencesFU Berlin Winterseminar (slides)
27.2.2017Kernel Methods in Machine LearningZuse Institute Berlin (slides)
8.6.2016Gradient IS and Unadjusted Langevin for ISMachine Learning group, HU Berlin
25.4.2016Kernel Sequential Monte Carlo University of Oxford (slides)
22.4.2016Kernel Sequential Monte Carlo University College London (slides)
19.4.2016Gradient IS and Unadjusted Langevin for IS University of Reading, Afternoon on Bayesian Computation (slides)
11.3.2016Gradient Importance SamplingFU Berlin (slides)
3.12.2015Kernel Adaptive Sequential Monte CarloBayes in Paris, ENSAE Paris (slides)
8.6.2015Bayesian Model Selection for Natural Language Semantics and Iterated Importance Sampling using Gradient InformationComputerlinguistisches Kolloquium, Universität Potsdam
16.4.2015Adaptive Monte Carlo based on Importance Sampling: A gradient-informed algorithmMPI for Intelligent Systems, Tübingen
13.2.2015Consistency of IS based on dependent sample setsBayes in Paris, ENSAE Paris
5.11.2014Probabilistic Models of Natural Language SemanticsKorpuslinguistisches Kolloquium, HU Berlin


Stochastic gradient methods for Monte Carlo and variational inferenceWorkshop at MCM 2017
Recent advances in importance samplingWorkshop at MCQMC 2016