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 deep generative models (including large language models), resource-efficient inference methods, model compression, and applications of probabilistic machine-learning methods to natural sciences. We typically focus on developing new algorithms and approximation techniques that apply to a large family of models rather than improving a single model architecture, and we aim at developing practical methods guided by computational constraints and theoretical insights. Here, computational constraints focus on memory, bandwidth, and run-time limitations of real hardware (e.g., GPUs), and theoretical insights are usually based in statistics, information theory, or come from idea transfer from my background in theoretical physics.
Find out more about my group at our group website.
I became a professor at 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 (a part of Walt Disney Imagineering) 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.
Machine Learning Publications
Representative publications include improvements to black box variational inference (BBVI) and applications of BBVI to neural data compression, to time series models, and to natural sciences, as well as resource efficient learning algorithms. For more publications, see list below.
-
Verbalized Machine Learning: Revisiting Machine Learning with Language ModelsTMLR 2025PDF
-
Your Finetuned Large Language Model is Already a Powerful Out-of-distribution DetectorAISTATS 2025 (accepted)PDF
-
Balancing Molecular Information and Empirical Data in the Prediction of Physico-Chemical PropertiesDigital Discovery, 2025PDF Journal Website
-
A Note on Generalization in Variational Autoencoders: How Effective Is Synthetic Data & Overparameterization?TMLR, 2024PDF
-
FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep LearningNeurIPS 2024PDF
-
Predictive, scalable and interpretable knowledge tracing on structured domainsICLR 2024PDF
-
Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target DistributionICML 2024PDF
-
A Compact Representation for Bayesian Neural Networks By Removing Permutation SymmetryNeurIPS 2023 Workshop on Unifying Representations in Neural ModelsPDF
-
The SVHN Dataset Is Deceptive for Probabilistic Generative Models Due to a Distribution MismatchNeurIPS 2023 Workshop on Distribution ShiftsPDF
-
Resampling Gradients Vanish in Differentiable Sequential Monte Carlo SamplersICLR 2023 (TinyPapers track)PDF
-
Trading Information between Latents in Hierarchical Variational AutoencodersICLR 2023PDF
-
Post-Training Neural Network Compression With Variational Bayesian QuantizationNeurIPS 2022 Workshop on Challenges in Deploying and Monitoring Machine Learning SystemsPDF
-
Making thermodynamic models of mixtures predictive by machine learning: matrix completion of pair interactionsChemical Science 13 (17), 4854-4862PDF
-
Improving Inference for Neural Image CompressionNeurIPS 2020PDF
-
User-Dependent Neural Sequence Models for Continuous-Time Event DataNeurIPS 2020PDF
-
Hybridizing physical and data-driven prediction methods for physicochemical propertiesChemical Communications, 2020PDF Journal 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 InferenceNeurIPS 2017PDF
-
Bayesian Paragraph VectorsNeurIPS 2017 workshop on Advances in Approximate Bayesian InferencePDF
-
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)