Robert Bamler
I am a Professor of Data Science and Machine Learning at University of Tübingen, Germany, and a member of the Cluster of Excellence "Machine Learning: New Perspectives for Science" and Tübingen AI Center.
My group performs research on scalable approximate Bayesian inference methods (especially variational methods) and on deep probabilistic models, with applications to neural data compression and natural sciences. We also use ideas from Bayesian inference to work towards a radically new kind of equitable distributed machine learning on decentralized networks such as blockchains. Our research is at the intersection of probabilistic models, efficient inference algorithms, and novel powerful approximation techniques. The latter are often inspired by ideas from natural sciences due to my personal background in statistical physics.
I joined University of Tübingen and the Cluster of Excellence for Machine Learning in November 2020. Before this, I was a postdoctoral scholar in the statistical machine learning group of UC Irvine lead by Stephan Mandt, and before that I was a machine learning researcher at Disney Research in Pittsburgh and Los Angeles. I received my PhD in theoretical statistical and quantum physics from University of Cologne in 2016, advised by Achim Rosch and with support from German Telekom Foundation.
News
1/2021 | I feel honored to be part of this year's jury for Jugend Forscht, a prestigious science fair under the auspices of the President of Germany. This contest truly encourages creativity—the only assignment for participating high school students is: "do something interesting". |
---|---|
11/2020 | I've been appointed Professor of Data Science and Machine Learning at University of Tübingen, the Cluster of Excellence "Machine Learning: New Perspectives for Science", and Tübingen AI Center. I am very excited to build up a new research group here at one of the most vibrant environments for machine learning research in Europe. Please reach out to me if you are interested in joining my group as a PhD or postdoctoral researcher. |
9/2020 | Two NeurIPS papers accepted: "Improving Inference for Neural Image Compression" and "User-Dependent Neural Sequence Models for Continuous-Time Event Data". Congratulations to the students Yibo Yang and Alex Boyd! |
9/2020 | Chemical Communications has accepted our paper "Hybridizing physical and data-driven prediction methods for physicochemical properties". |
Machine Learning Publications
Representative publications include improvements to black box variational inference (BBVI) and applications of BBVI to time series models, to deep neural data compression, and to natural sciences, as well as resource efficient learning algorithms. For more publications, see list below.
-
Improving Inference for Neural Image CompressionNeurIPS 2020 (accepted)PDF
-
User-Dependent Neural Sequence Models for Continuous-Time Event DataNeurIPS 2020 (accepted)PDF
-
Hybridizing physical and data-driven prediction methods for physicochemical propertiesChemical Communications, 2020Journal Website
-
Variational Bayesian Quantization(former title: Variable-Bitrate Neural Compression via Bayesian Arithmetic Coding)ICML 2020PDF Vide abstract by Yibo Yang (15 min)
-
Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix CompletionThe Journal of Physical Chemistry Letters, 2020(11) 981-985PDF Journal website
-
Extreme Classification via Adversarial Softmax ApproximationICLR 2020PDF Video abstract (5 min.) Slides
-
Tightening Bounds for Variational Inference by Revisiting Perturbation TheoryJ. Stat. Mech. (2019) 124004PDF Journal website
-
Augmenting and Tuning Knowledge Graph EmbeddingsUAI 2019PDF Video abstract (1 min.) Slides
-
Improving Optimization for Models With Continuous Symmetry BreakingICML 2018PDF Related video abstract (4 min.) Slides
-
Perturbative Black Box Variational InferenceNIPS 2017PDF
-
Dynamic Word EmbeddingsICML 2017PDF Promotional video (3 min.) Conference talk (17 min.)
Physics Publications
-
Phase-Space Berry Phases in Chiral Magnets: Skyrmion Charge, Hall Effect, and Dynamics of Magnetic SkyrmionsPh.D. thesis, University of Cologne (2016)PDF
-
Equilibration and approximate conservation laws: Dipole oscillations and perfect drag of ultracold atoms in a harmonic trapPhys. Rev. A 91, 063604 (2015)PDF
-
Phase-space Berry phases in chiral magnets: Dzyaloshinskii-Moriya interaction and the charge of skyrmionsPhys. Rev. B 88, 214409 (2013)PDF
-
Giant generic topological Hall resistivity of MnSi under pressurePhys. Rev. B 87, 134424 (2013)PDF
-
Hydrodynamic Object Recognition: When Multipoles CountPhys. Rev. Lett. 102, 058104 (2009)PDF
Talks & Video Abstracts
Below is a selection of talks and video abstracts where either recordings or slides are available.
-
Scalable Bayesian Inference: New Tools for New Challengesml4science Cluster Colloquium, University of Tübingen, Germany, 2/2021Video recording (50 min.) Slides
-
Extreme Classification via Adversarial Softmax ApproximationICLR 2020Video abstract (5 min.) Slides Paper (PDF)
-
Revisiting Variational Expectation MaximizationAI/ML Seminar @ UC Irvine, 2019Slides Related paper 1 (PDF) Related paper 2 (PDF)
-
Marrying Big Data And Probabilistic Models With Variational InferenceGerman Aerospace Center (DLR), 2019Slides
-
Augmenting and Tuning Knowledge Graph EmbeddingsUAI 2019Video abstract (1 min.) Slides Paper (PDF)
-
A Quantum Field Theory of Representation LearningTheoretical Physics for Deep Learning Workshop at ICML 2019Video abstract (4 min.) Slides Workshop paper (PDF) Related paper (PDF)
-
Dynamic Word EmbeddingsICML 2017Video recording (17 min.) Paper (PDF)