[ Bio  Research  News  Teaching  Group  Publications  Github ]
Short Bio
Stephan Mandt is an Associate Professor of Computer Science and Statistics at the University of California, Irvine. Previously, he led the machine learning group at Disney Research in Pittsburgh and Los Angeles and held postdoctoral positions at Princeton and Columbia University. Stephan holds a Ph.D. in Theoretical Physics from the University of Cologne, where he received the German National Merit Scholarship. He is furthermore a recipient of the NSF CAREER Award, the UCI ICS MidCareer Excellence in Research Award, the German Research Foundation's Mercator Fellowship, a Kavli Fellow of the U.S. National Academy of Sciences, a member of the ELLIS Society, and a former visiting researcher at Google Brain. His research is currently supported by NSF, DARPA, IARPA, DOE, Disney, Intel, and Qualcomm. Stephan is an Action Editor of the Journal of Machine Learning Research and Transaction on Machine Learning Research, held tutorials at NeurIPS, AAAI, and UAI, and regularly serves as an Area Chair for NeurIPS, ICML, AAAI, and ICLR. He currently serves as Program Chair for AISTATS 2024 and will continue to serve as General Chair for AISTATS 2025.
Research Interests
The following research areas are of interest to the group:
PhD student applicants: Unfortunately, I will not be able to respond to most inquiries regarding PhD openings or comment on your applications to my group. If you indicate your interests to work with me in the application questions, I will make sure to review them carefully. Online Application page.
UCI undergraduate students, read this first: Thank you for your interest in working on research projects with us. Due to the high demand for generative AI opportunities we can only accommodate a limited number of students each year. When reaching out, kindly include your resume and UCI transcript and describe what kind of research interests you the most. You should have already excelled in CS 178 with a top grade (A or A+) and ideally have taken additional courses in AI/ML. Your understanding of these constraints is greatly appreciated.
News
 Accepted papers in 2023: 1 x AISTATS, 2 x ICML, 1 x UAI, 2 x ICCV, 4 x NeurIPS, 3 journal papers.
 I will serve as Program Chair for AISTATS 2024 (with Yingzhen Li).
 I received the Mercator Fellowship of the German National Science Foundation.
 I'm happy to have received the Dean's MidCareer Award for Excellence in Research.
 Accepted papers in 2022: 2 x ICML, 2 x ICLR, IJCAI, WACV, NeurIPS, 2 journal papers
 I'm honored to have received the NSF CAREER Award for "Variational Inference for ResourceEfficient Learning".
 Selected recent talk recordings:
 Neural Compression Tutorial at NeurIPS 2022
 Compressing Variational Bayes (Vector Institute, 2021)
 Generative Modeling of Structured Data (Kavli Frontiers of Science, National Academy of Sciences, 2019)
 Machine Learning and Physics: Bridging the Gap (TopDyn Conference, 2020)
 Accepted papers in 2021: NeurIPS, ICML, ICLR, AISTATS, 1 journal paper
 Recent workshop & conference organization:
 ICLR Workshop on Neural Compression: From Information Theory to Applications, 2021
 Southern California Machine Learning and NLP Symposium, 2021
 3rd Symposium on Advances on Approximate Bayesian Inference, 2020
 Area Chair for NeurIPS 2021, ICML 2021, ICLR 2021, NeurIPS 2020, ICML 2020, AAAI 2020, NeurIPS 2019, ICML 2019
 Recent Grants:
 Department of Energy grant on probabilistic machine learning for climate science (UCI PI)
 NSF CAREER Award on Variational Inference for ResourceEfficient Learning
 NSF/Intel grant on machine learning for UAVs and semantic compression (CoPI)
 NSF CISE RI Small grant on Deep Variational Data Compression (single PI)
 Darpa grant on openworld novelty detection (UCI PI)
 Hasso Plattner Institute at UCI (CoDirector)
 Unrestricted gifts from Qualcomm (PI)
Teaching
 Fall 2023: Deep Generative Models (graduate) (CS 274E)
 Fall 2022: Deep Generative Models (graduate) (CS 274E)
 Winter 2022:
 Machine Learning and Data Mining (undergraduate) (CS 178)
 Introduction to Machine Learning (graduate) (CS 273A)
 Fall 2021: Deep Generative Models (graduate) (CS 274E)
 Spring 2021: Machine Learning and Data Mining (graduate) (CS 178)
 Fall 2020: Introduction to Machine Learning (undergraduate) (CS 273A)
 Spring 2020: Deep Generative Models (graduate) (CS 295)
 Winter 2020: Machine Learning and Data Mining (undergraduate) (CS 178)
 Fall 2019: Introduction to Machine Learning (graduate) (CS 273A)
 Spring 2019: Deep Generative Models (graduate) (CS 295)
Group Members
Current:Former:
 Efficient Integrators for Diffusion Generative Models
K. Pandey, M. Rudolph, and S. Mandt
2310.07894 PDF  Comparing Storm Resolving Models and Climates via Unsupervised Machine Learning
G. Mooers, M. Pritchard, T. Beucler, P. Srivastava, H. Mangipudi, L. Peng, P. Gentine, and S. Mandt
arXiv:2208.11843 PDFPublications
2023

Estimating the RateDistortion Function by Wasserstein Gradient Descent
Y. Yang, S. Eckstein, M. Nutz, and S. Mandt
Neural Information Processing Systems (NeurIPS 2023), accepted PDF 
Lossy Image Compression with Conditional Diffusion Models
R. Yang and S. Mandt
Neural Information Processing Systems (NeurIPS 2023), accepted PDF 
ZeroShot BatchLevel Anomaly Detection
A. Li, C. Qiu, M. Kloft, P. Smyth, M. Rudolph, and S. Mandt
Neural Information Processing Systems (NeurIPS 2023), accepted PDF 
ClimSim: An open largescale dataset for training highresolution physics emulators in hybrid multiscale climate simulators
S. Yu et al.
Neural Information Processing Systems (NeurIPS 2023), accepted PDF  Diffusion Probabilistic Modeling for Video Generation
R. Yang, P. Srivastava, and S. Mandt
Entropy 25 (10), 1469 PDF 
Computationally Efficient Neural Image Compression with Shallow Decoders
Y. Yang and S. Mandt
International Conference on Computer Vision (ICCV 2023) PDF 
Generative Diffusions in Augmented Spaces: A Complete Recipe
K. Pandey and S. Mandt
International Conference on Computer Vision (ICCV 2023)(Oral) PDF 
Inference for MarkCensored Temporal Point Processes
A. Boyd, Y. Chang, S. Mandt, and P. Smyth
Uncertainty in Artificial Intelligence (UAI 2023)(Spotlight) PDF  SC2 Benchmark: Supervised Compression for Split Computing
Y. Matsubara, M. Levorato, and S. Mandt
Transactions on Machine Learning Research, 2023 PDF  An Introduction to Neural Data Compression
Y. Yang, S. Mandt, and L. Theis
Foundations and Trends in Computer Graphics and Vision, 2023 PDF  Insights from Generative Modeling for Neural Video Compression
R. Yang, Y. Yang, J. Marino, and S. Mandt
Transactions on Pattern Analysis and Machine Intelligence, 2023 preprint 
Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes
B. Tran, B. Shahbaba, S. Mandt, M. Filippone
International Conference on Machine Learning (ICML 2023) PDF 
Deep Anomaly Detection under Labeling Budget Constraints
A. Li, C. Qiu, P. Smyth, M. Kloft, S. Mandt, M. Rudolph
International Conference on Machine Learning (ICML 2023) PDF 
Probabilistic Querying of ContinuousTime Event Sequences
A. Boyd, Y. Chang, S. Mandt, and P. Smyth
Artificial Intelligence and Statistics (AISTATS 2023) PDF2022

Predictive Querying for Autoregressive Neural Sequence Models
A. Boyd, S. Showalter, S. Mandt, and P. Smyth
Neural Information Processing Systems (NeurIPS 2022) (Oral) PDF  An Unsupervised Learning Perspective on the Dynamic Contribution to Extreme Precipitation Changes
G. Mooers, T. Beucler, M. Pritchard, and S. Mandt
NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning PDF  Latent Outlier Exposure for Anomaly Detection with Contaminated Data
C. Qiu, A. Li, M. Kloft, M. Rudolph, and S. Mandt
International Conference on Machine Learning (ICML 2022) PDF  Structured Stochastic Gradient MCMC
A. Alexos, A. Boyd, and S. Mandt
International Conference on Machine Learning (ICML 2022) PDF poster code 
Raising the Bar in Graphlevel Anomaly Detection
C. Qiu, M. Kloft , S. Mandt, and M. Rudolph
International Joint Conference on Artificial Intelligence (IJCAI 2022) PDF 
Learning to Simulate High Energy Particle Collisions from Unlabeled Data
J. Howard, S. Mandt, D. Whiteson, Y. Yang
Nature Scientific Reports 12, 7567 (2022) PDF 
Making Thermodynamic Models of Mixtures Predictive by Machine Learning: Matrix Completion of Pair Interactions
F. Jirasek, R. Bamler, S. Fellenz, M. Bortz, M. Kloft, S. Mandt, and H. Hasse
Chemical Science 13, 48544862 (2022) PDF  Towards Empirical Sandwich Bounds on the RateDistortion Function
Y. Yang and S. Mandt
International Conference on Learning Representations (ICLR 2022) PDF  Lossless Compression with Probabilistic Circuits
A. Liu, S. Mandt, and G. van den Broeck
International Conference on Learning Representations (ICLR 2022) PDF  Supervised Compression for ResourceConstrained Edge Computing Systems
Y. Matsubara, R. Yang, M. Levorato, and S. Mandt
Winter Conference on Applications of Computer Vision (WACV 2022) arXiv2021
 Improving Sequential Latent Variable Models with Autoregressive Flows
J. Marino, J. He, L. Chen, and S. Mandt
Machine Learning (2021) article.  History Marginalization Improves Forecasting in Variational Recurrent Neural Networks
C. Qiu, S. Mandt, and M. Rudolph
Entropy 23, 1563 (2021) article.  Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning
A. Li, A. Boyd, P. Smyth, S. Mandt
Neural Information Processing Systems (NeurIPS 2021). PDF.  Neural Transformation Learning for Deep Anomaly Detection Beyond Images
C. Qiu, T. Pfrommer, M. Kloft, S. Mandt, and M. Rudolph
International Conference on Machine Learning (ICML 2021). PDF  Hierarchical Autoregressive Modeling for Neural Video Compression
R. Yang, Y. Yang, J. Marino, and S. Mandt
International Conference on Learning Representations (ICLR 2021). PDF  Scale Space Flow with Autoregressive Priors
R. Yang, Y. Yang, J. Marino, and S. Mandt
ICLR Workshop on Neural Compression: from Information Theory to Applications, 2021 (Spotlight). PDF  Lower Bounding RateDistortion from Samples
Y. Yang and S. Mandt
ICLR Workshop on Neural Compression: from Information Theory to Applications, 2021 (Spotlight). PDF  Scalable Gaussian Process Variational Autoencoders
M. Jazbec, M. Ashman, V. Fortuin, M. Pearce, S. Mandt, and G. Rätsch
Artificial Intelligence and Statistics (AISTATS 2021). PDF2020

Improving Inference for Neural Image Compression
Y. Yang, R. Bamler, and S. Mandt
Neural Information Processing Systems (NeurIPS 2020). PDF code 
UserDependent Neural Sequence Models for ContinuousTime Event Data
A. Boyd, R. Bamler, S. Mandt, and P. Smyth
Neural Information Processing Systems (NeurIPS 2020). PDF 
Hybridizing Physical and DataDriven Prediction Methods for Physicochemical Properties
F. Jirasek, R. Bamler, and S. Mandt
Chemical Communications 56 12407, 2020 article 
Generative Modeling for Atmospheric Convection
G. Mooers, J. Tuyls, S. Mandt, M. Pritchard, and T. Beucler
Climate Informatics, 2020 PDF 
Variational Bayesian Quantization
Y. Yang, R. Bamler, and S. Mandt
International Conference on Machine Learning (ICML 2020) PDF Video 
How Good is the Bayes Posterior in Deep Neural Networks Really?
F. Wenzel, K. Roth, B. Veeling, J. Swiatkowski, L. Tran, S. Mandt, J. Snoek, T. Salimans, R. Jenatton, and S. Nowozin
International Conference on Machine Learning (ICML 2020) PDF 
The ktied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
J. Swiatkowski, K. Roth, B. Veeling, L. Tran, J. Dillon, S. Mandt, J. Snoek, T. Salimans, R. Jenatton, and S. Nowozin
International Conference on Machine Learning (ICML 2020) PDF  Hydra: Preserving Ensemble Diversity for Model Distillation
L. Tran, B. Veeling, K. Roth, J. Swiatkowski, J. Dillon, J. Snoek, S. Mandt, T. Salimans, S. Nowozin, R. Jenatton
arXiv:2001.04694 PDF 
Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completion
F. Jirasek, R. Alves, J. Damay, R. Vandermeulen, R. Bamler, M. Bortz, S. Mandt, M. Kloft, and H. Hasse
The Journal of Physical Chemistry Letters, 11, 2020. article free PDF 
GPVAE: Deep Probabilistic Time Series Imputation
V. Fortuin, D. Baranchuk, G. Rätsch, and S. Mandt
Artificial Intelligence and Statistics (AISTATS 2020). PDF 
Extreme Classification via Adversarial Softmax Approximation
R. Bamler and S. Mandt
International Conference on Learning Representations (ICLR 2020). PDF2019

Tightening Bounds for Variational Inference by Revisiting Perturbation Theory
R. Bamler, C. Zhang, M. Opper, and S. Mandt
Journal of Statistical Mechanics (2019), 124004. PDF 
Deep Generative Video Compression
J. Han, S. Lombardo, C. Schroers, and S. Mandt
Neural Information Processing Systems (NeurIPS 2019). PDF poster 
Autoregressive Text Generation Beyond Feedback Loops
F. Schmidt, S. Mandt, and T. Hofmann
Conference on Empirical Methods in Natural Language Processing (EMNLP 2019). PDF 
Augmenting and Tuning Knowledge Graph Embeddings
R. Bamler, F. Salehi, and S. Mandt
Conference on Uncertainty in Artificial Intelligence (UAI 2019). PDF 
Advances in Variational Inference
C. Zhang, J. Bütepage, H. Kjellström, and S. Mandt
IEEE Transactions on Pattern Analysis and Machine Intelligence. PDF arXiv 
Active MiniBatch Sampling using Repulsive Point Processes
C. Zhang, C. Öztireli, S. Mandt, and G. Salvi
Conference on Artificial Intelligence (AAAI 2019). article PDF 
Mobile Robotic Painting of Texture
M. Helou, S. Mandt, A. Krause, and P. Beardsley
International Conference on Robotics and Automation (ICRA 2019). article PDF 
A Quantum Field Theory of Representation Learning
R. Bamler and S. Mandt
ICML Workshop on Physics for Deep Learning (2019). PDF2018

Disentangled Sequential Autoencoder
Y. Li and S. Mandt
International Conference on Machine Learning (ICML 2018). PDF 
Iterative Amortized Inference
J. Marino, Y. Yue, and S. Mandt
International Conference on Machine Learning (ICML 2018). PDF 
Quasi Monte Carlo Variational Inference
A. Buchholz, F. Wenzel, and S. Mandt
International Conference on Machine Learning (ICML 2018). PDF 
Improving Optimization for Models With Continuous Symmetry Breaking
R. Bamler and S. Mandt
International Conference on Machine Learning (ICML 2018), long talk. PDF 
Continuous Word Embedding Fusion via Spectral Decomposition
T. Fu, C. Zhang, and S. Mandt
The SIGNLL Conference on Natural Language Learning (CoNLL 2018). PDF 
Scalable Generalized Dynamic Topic Models
P. Jähnichen, F. Wenzel, M. Kloft, and S. Mandt
Artificial Intelligence and Statistics (AISTATS 2018). PDF 
Image Anomaly Detection with Generative Adversarial Networks
L. Deecke, R. Vandermeulen, L. Ruff, S. Mandt, and M. Kloft
European Conference on Machine Learning (ECML PKDD 2018). PDF 
Learning to Infer
J. Marino, Y. Yue, and S. Mandt
International Conference on Learning Representations (Workshop Track). PDF 
Quasi Monte Carlo Flows
F. Wenzel, A. Buchholz, and S. Mandt
NeurIPS Bayesian Deep Learning Workshop. PDF 
Video Compression through Deep Bayesian Learning
S. Lombardo, J. Han, C. Schroers, and S. Mandt
NeurIPS Bayesian Deep Learning Workshop. PDF2017

Stochastic Gradient Descent as Approximate Bayesian Inference
S. Mandt, M. Hoffman, and D. Blei
Journal of Machine Learning Research, vol 18(134):135, 2017. PDF code 
Perturbative Black Box Variational Inference
R. Bamler, C. Zhang, M. Opper, and S. Mandt
Neural Information Processing Systems (NIPS 2017). PDF poster 
Dynamic Word Embeddings
R. Bamler and S. Mandt
International Conference on Machine Learning (ICML 2017). PDF poster 
Determinantal Point Processes for Minibatch Diversification
C. Zhang, H. Kjellström, and S. Mandt
Uncertainty in Artificial Intelligence (UAI 2017) (plenary talk). PDF 
Factorized Variational Autoencoders for Modeling Audience Reactions to Movies
Z. Deng, R. Navarathna, P. Carr, S. Mandt, Y. Yue, I. Matthews, and G. Mori
Computer Vision and Pattern Recognition (CVPR 2017). PDF 
Iterative Inference Models
J. Marino, Y. Yue, and S. Mandt
NIPS 2017 Workshop on Bayesian Deep Learning. PDF 
Bayesian Paragraph Vectors
G. Ji, R. Bamler, E. Sudderth, and S. Mandt
NIPS 2017 Workshop on Approximate Bayesian Inference. PDF 
Structured Black Box Variational Inference for Latent Time Series Models
R. Bamler and S. Mandt
ICML 2017 Time Series Workshop (oral). PDF 
Diversified MiniBatch Sampling using Repulsive Point Processes
C. Zhang, C. Öztireli, and S. Mandt
NIPS 2017 Workshop on Advances in Approximate Bayesian Inference. PDF2016

Exponential Family Embeddings
M. Rudolph, F.J.R. Ruiz, S. Mandt, and D. Blei
Neural Information Processing Systems (NIPS 2016). PDF 
Balanced Population Stochastic Variational Inference
C. Zhang, S. Mandt, and H. Kjellström
NIPS 2016 Workshop on Advances in Approximate Bayesian Inference. PDF 
HuberNorm Regularization for Linear Prediction Models
O. Zadorozhnyi, G. Benecke, S. Mandt, T. Scheffer, M. Kloft
European Conference on Machine Learning (ECML 2016). PDF 
A Variational Analysis of Stochastic Gradient Algorithms
S. Mandt, M. Hoffman, and D. Blei
International Conference on Machine Learning (ICML 2016) PDF poster video
code 
Variational Tempering
S. Mandt, J. McInerney, F. Abrol, R. Ranganath, and D. Blei
Artificial Intelligence and Statistics (AISTATS 2016). PDF 
Separating Sparse Signals from Correlated Noise in Binary Classification
S. Mandt, F. Wenzel, S. Nakajima, C. Lippert, and M. Kloft.
UAI 2016 Workshop on Causation: Foundation to Application. (oral) PDF2015

Sparse Probit Linear Mixed Model
S. Mandt, F. Wenzel, S. Nakajima, J. P. Cunningham, C. Lippert, and M. Kloft
Machine Learning, 106(9), 16211642. PDF 
ContinuousTime Limit of Stochastic Gradient Descent Revisited
S. Mandt, M. Hoffman, and D. Blei
NIPS Workshop on Optimization for Machine Learning (OPT 2015) PDF 
Finding Sparse Features in Strongly Confounded Medical Binary Data
S. Mandt, F. Wenzel, S. Nakajima, J. P. Cunningham, C. Lippert, and M. Kloft
NIPS Workshop on Machine Learning in Healthcare (2015). (oral) PDF 
Stochastic Differential Equations for Quantum Dynamics of SpinBoson Networks
S. Mandt, D. Sadri, A. Houck, and H. Tureci
New Journal of Physics 17 (2015) 053018. PDF2014

Smoothed Gradients for Stochastic Variational Inference
S. Mandt and D. Blei
Neural Information Processing Systems (NIPS 2014) PDF 
Probit Regression with Correlated Label Noise: An EMEP approach
S. Mandt, F. Wenzel, J. Cunningham, and M. Kloft
NIPS Workshop on Advances in Variational Inference (2014) PDF 
Comment on "Consistent thermostatistics forbids negative absolute temperatures"
U. Schneider, S. Mandt, A. Rapp, S. Braun, H. Weimer, I. Bloch, and A. Rosch
Arxiv (2014). PDF 
Damping of Bloch oscillations: Variational solution of the Boltzmann equation beyond linear response
S. Mandt
Physical Review A 90, 053624 (2014). PDFBefore 2014

Relaxation towards negative temperatures in bosonic systems: Generalized Gibbs ensembles and beyond integrability
S. Mandt, A. Feiguin, S. Manmana
Physical Review A 88, 043643 (2013). PDF 
Ultrakalt und doch heißer als unendlich heiß. Erstmals gelang es, ein Quantengas bei negativen absoluten Temperaturen herzustellen
S. Mandt
Popular article on negative temperatures in the monthly proceedings of the German Physical Society.
Physik Journal 12, March edition (2013) PDF 
Transport and NonEquilibrium Dynamics in Optical Lattices. From Expanding Atomic Clouds to Negative Absolute Temperatures
S. Mandt
PhD thesis, University of Cologne (2012) PDF 
Fermionic transport in a homogeneous Hubbard model: Outofequilibrium dynamics with ultracold atoms
U. Schneider, L. Hackermueller, J.P. Ronzheimer, S. Will, S. Braun, T. Best, I. Bloch, E. Demler, S. Mandt, D. Rasch, A. Rosch
Nature Physics 8, 213218 (2012). PDF
Press: SciTechDaily, ProPhysik (in German) 
Interacting Fermionic Atoms in Optical Lattices Diffuse Symmetrically Upwards and Downwards in a Gravitational Potential
S. Mandt, A. Rapp, A. Rosch
Physical Review Letters 106, 250602 (2011). arXiv
Press: Nature 
Equilibration rates and negative absolute temperatures for ultracold atoms in optical lattices
A. Rapp, S. Mandt, A. Rosch
Physical Review Letters 105, 220405 (2010). arXiv
Press: Nature , New Scientist, Science News
Experimental realization of T<0 based on our theory: Braun et. al., Science 2013 
Zooming in on local level statistics by supersymmetric extension of free probability
S. Mandt, M.R. Zirnbauer
J. Phys. A 43 (2010) 025201. arXiv 
Symmetric Spaces Toolkit
H. Sebert and S. Mandt
Lecture notes, SFB/TR 12, Langeoog (2007) PDF