[
Bio

News

Teaching

Research

Publications

Talks

CV
]
Short Bio
I am an Assistant Professor of Computer Science at the University of California, Irvine. From 2016 until September 2018, I was a Senior Researcher and head of the statistical machine learning group at Disney Research, first in Pittsburgh and later in Los Angeles. I held previous positions as a postdoc with David Blei at
Columbia University (20142016), and as a PCCM Postdoctoral Fellow at Princeton University (20122014). My Ph.D. advisor was Achim Rosch
at the Institute
for Theoretical Physics of the University of Cologne. I was a fellow of the German Academic Merit Foundation.
News
 I gave an invited talk at the National Academy of Science's Kavli Frontiers of Science Symposium
 I will serve as an Area Chair for ICML 2019 and NeurIPS 2019.
 I was invited to present at the workshop At the Crossroad of Physics and Machine Learning in Santa Barbara.
 Our workshop series on Approximate Bayesian Inference was offered as a Symposium this year, colocated with NeurIPS 2018.
 I joined the School of Information and Computer Sciences at the University of California, Irvine.
 Four accepted papers at ICML 2018.
 Accepted papers at AISTATS 2018, NIPS 2017, UAI 2017, ICML 2017 and CVPR 2017.
 Two journal papers accepted in 2017 (MLJ and JMLR).
 Accepted papers at AISTATS 2016, ICML 2016, and NIPS 2016.
 Coorganizer, NIPS Workshop on Advances on Approximate Bayesian Inference (2017, 2016, 2015)
Teaching
CS 295: Deep Generative Models (Spring 2019)
Research Interests
My primary goal is to develop a new generation of machine learning models by drawing on deep learning, probabilistic graphical models, and approximate Bayesian inference. My research, thus, tries to synthesize representation learning and probabilistic modeling. This results in new flexible and oftentimes interpretable models for unsupervised or semisupervised learning on large data.
My group has developed several such models for various applications, in particular for sequential data. Dynamic Word Embeddings (ICML'17) combine word embeddings with probabilistic Kalman filters, allowing us to accurately measure how words change their meanings over hundreds of years while keeping track of uncertainty due to data sparsity. Factorized Variational Autoencoders (CVPR'17) helped us discover latent factors in audience face reactions to movie screenings. Disentangled Sequential Autoencoders (ICML'18) enabled us to generate artificial videos while gaining partial control over content and dynamics.
My second goal is to design new learning and inference algorithms which are scalable and generic. I frequently use a methodology termed variational inference, an approximation scheme that allows generative models to be trained on massive scales. Relevant papers in this line of research are Stochastic Gradient Descent as Approximate Bayesian Inference (JMLR'17), Variational Tempering (AISTATS'16), QuasiMonte Carlo Variational Inference (ICML'18), Iterative Amortized Inference (ICML'18), and Perturbative Black Box Variational Inference (NIPS'17). We also recently published a review article on this topic.
I am interested in a wide range of applications, including computer vision, natural language processing, media analytics, and applications in the sciences.
Representative Publications

Stochastic Gradient Descent as Approximate Bayesian Inference
S. Mandt, M. Hoffman, and D. Blei
Journal of Machine Learning Research 18, 135, 2017. [PDF]

Dynamic Word Embeddings
R. Bamler and S. Mandt
International Conference on Machine Learning 2017. [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 2017. [PDF]

Exponential Family Embeddings
M. Rudolph, F.J.R. Ruiz, S. Mandt, and D. Blei
Neural Information Processing Systems 2016. [PDF]

Improving Optimization in Models with Continuous Symmetry Breaking
R. Bamler and S. Mandt
International Conference on Machine Learning 2018. [PDF]

Perturbative Black Box Variational Inference
R. Bamler, C. Zhang, M. Opper, and S. Mandt
Neural Information Processing Systems 2017. [PDF]
All Publications
Preprints

Deep Probabilistic Video Compression
J. Han, S. Lombardo, C. Schroers, and S. Mandt
arxiv preprint. [arXiv]
2019

Advances in Variational Inference
C. Zhang, J. Bütepage, H. Kjellström, and S. Mandt
IEEE Transactions on Pattern Analysis and Machine Intelligence. [PDF]

Active MiniBatch Sampling using Repulsive Point Processes
C. Zhang, C. Öztireli, S. Mandt, and G. Salvi
AAAI 2019. [PDF]

Mobile Robotic Painting of Texture
M. Helou, S. Mandt, A. Krause, and P. Beardsley
International Conference on Robotics and Automation (ICRA 2019), to appear.
2018

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).

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. [PDF]
2017

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. [PDF]
2016

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) [PDF]
2015

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.
[PDF]
2014

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). [arXiv]

Damping of Bloch oscillations: Variational solution of the Boltzmann equation beyond linear response
S. Mandt
Physical Review A 90, 053624 (2014). [arXiv]
Before 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). [arXiv]

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). [arXiv]
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]
Invited Talks
 CS Colloquium, EPFL Lausanne
Lausanne, Switzerland. October 2017.
 ML Lunch Seminar, Carnegie Mellon University
Pittsburgh, PA. September 2017.
 Disney Data Analytics Conference
Orlando, FL. August 2017.
 CS Colloquium, University of Southern California
Los Angeles, CA. April 2017.
 CS Colloquium, ETH Zürich
Zürich, Switzerland. March 2017.

ML and Friends Seminar, UMass Amherst
Amherst, MA. February 2017.
 AI Seminar, Carnegie Mellon University
Pittsburgh, PA. September 2016.
 California Institute of Technology
Pasadena, CA. August 2016.
 Data Science Colloquium, Rutgers University
Newark, NJ. April 2016.
 Google Research
Mountain View, CA. April 2016.
 Microsoft
Sunnyvale, CA. March 2016.
 CS Colloquium, University of Rhode Island
Kingston, RI. March 2016.
 Disney Research
Pittsburgh, Pennsylvania. March 2016.
 CS Colloquium, University of Colorado
Boulder, Colorano. January 2016.
 National Renewable Energy Laboratory
Golden, Colorado. January 2016.
 Adobe Research
San Francisco, CA. June 2015.
 Human Longevity Inc.
Mountain View, CA. June 2015.
 Dagstuhl Seminar
Machine Learning with Interdependent and Nonidentically Distributed Data.
Dagstuhl, Germany. April 2015.
 Humboldt University of Berlin
Machine Learning Seminar, Berlin, Germany. February 2015.
 Technical University of Berlin
Machine Learning Seminar, Berlin, Germany. February 2015.
 DWave Systems Inc.
Burnaby, Canada. January 2015.
 University of British Columbia
Machine Learning Seminar, Vancouver, Canada. January 2015.
 IBM Research
Physical Sciences Seminar, Yorktown Heights, USA. October 2014.
 Emergent Phenomena in the Dynamics of Quantum Matter
(QUANTMAT 2014), New York, USA. April 2014.
 University of Otago
Theoretical Physics Seminar, Dunedin, New Zealand. February 2013.
 Princeton Center for Theoretical Science
Princeton University, Princeton, USA. March 2012.
 Finite Temperature NonEquilibrium Superfluid Systems
(FINESS 2011), Heidelberg, Germany  September 2011.
 University of Colorado
Theoretical Physics Seminar, Boulder, CO. September 2010.
 École Polytechnique
Theoretical Physics Seminar, Palaiseau, France. March 2010.