Stephan Mandt

Disney Research

[ bio | news | research | publications | talks | CV ]

Short Bio

I am currently a Senior Research Scientist and head of the statistical machine learning group at Disney Research, Los Angeles. Previously, I was a postdoctoral researcher with David Blei at Columbia University, (2014-2016), and a PCCM Postdoctoral Fellow at Princeton University in theoretical physics (2012-2014). 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.


  • We have just published a review article on variational inference on arxiv. Feedback is welcome.
  • Accepted papers at 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.
  • Co-organizer, NIPS 2017 Workshop on Advances on Approximate Bayesian Inference
  • Co-organizer, NIPS 2016 Workshop on Advanced in Approximate Bayesian Inference
  • Co-organizer, NIPS 2015 Workshop on Advanced in Approximate Bayesian Inference
  • We are offering research internships in the field of probabilistic machine learning. Internships are possible throughout the year and often result in a conference publication or patent. You should be available for 4-8 months and already have publications in the fields of machine learning, statistical NLP, or computer vision. If you are interested in working with me, please send me an email with your CV. (status: July 2017).

Research Interests

Keywords: variational inference; stochastic optimization; word embeddings; deep generative models

The field of probabilistic modeling has seen profound changes in the past few years, driven by advances in stochastic optimization, automatic differentiation, easy-to-use neural network packages, and the availability of large data sets. Building on these advances, modern variational inference and related training paradigms enabled a rich class of generative models that had been computationally intractable in the past. In particular, Bayesian deep learning and representation learning approaches have experienced a revival, which, in turn, had crucial implications for modern computer vision (GANs and VAEs) and natural language processing (word and paragraph embeddings). My research activities have driven these advances. My vision is to build algorithms and new expressive models that integrate the benefits of modern representation learning with interpretable probabilistic priors, and to apply these models in the domains of natural language processing, personalization and recommendation systems, computer vision, the sciences, and media analytics.



  • A Deep Generative Model for Disentangled Representations of Sequential Data
    Y. Li and S. Mandt
    arXiv preprint, 03/2018.   [PDF]
  • Improving Optimization for Models with Continuous Symmetry Breaking
    R. Bamler and S. Mandt
    arXiv preprint, 03/2018.   [PDF]
  • Scalable Generalized Dynamic Topic Models
    P. Jähnichen, F. Wenzel, M. Kloft, and S. Mandt
    Artificial Intelligence and Statistics (AISTATS 2018), to appear.


  • Advances in Variational Inference
    C. Zhang, J. Bütepage, H. Kjellström, and S. Mandt
    arxiv preprint, 11/2017.   [arXiv]
  • Perturbative Black Box Variational Inference
    R. Bamler, C. Zhang, M. Opper, and S. Mandt
    Neural Information Processing Systems (NIPS 2017).   [PDF]
  • Stochastic Gradient Descent as Approximate Bayesian Inference
    S. Mandt, M. Hoffman, and D. Blei
    Journal of Machine Learning Research, vol 18(134):1-35, 2017.   [PDF]
  • Determinantal Point Processes for Mini-batch Diversification
    C. Zhang, H. Kjellström, and S. Mandt
    Uncertainty in Artificial Intelligence (UAI 2017) (plenary talk).   [PDF]
  • Dynamic Word Embeddings
    R. Bamler and S. Mandt
    International Conference on Machine Learning (ICML 2017).   [PDF][poster]
  • 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]


  • 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]
  • Huber-Norm 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]
  • 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]


  • Sparse Probit Linear Mixed Model
    S. Mandt, F. Wenzel, S. Nakajima, J. P. Cunningham, C. Lippert, and M. Kloft
    Machine Learning, 106(9), 1621-1642.   [PDF]
  • Continuous-Time 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 Spin-Boson Networks
    S. Mandt, D. Sadri, A. Houck, and H. Tureci
    New Journal of Physics 17 (2015) 053018.   [PDF]


  • 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 EM-EP 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 Non-Equilibrium 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: Out-of-equilibrium 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, 213-218 (2012).   [arXiv]
    Press: SciTechDaily, Pro-Physik (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 Non-identically 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.
  • D-Wave 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 Non-Equilibrium 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.