Vincent Fortuin
Ph.D. Candidate, Computer Science
ETH Zürich, Institute for Machine Learning
Biomedical Informatics group
Email: fortuin at inf.ethz.ch



I am a PhD student in Computer Science at ETH Zürich under the supervision of Gunnar Rätsch and Andreas Krause and member of the Biomedical Informatics group as well as the ETH Center for the Foundations of Data Science. I am supported by a PhD fellowship from the Swiss Data Science Center and am also an ELLIS PhD student. My research focuses on the interface between deep learning and probabilistic modeling. I am particularly keen to develop models that are more interpretable and data efficient, following the Bayesian paradigm. To this end, I am mostly trying to improve deep probabilistic models with better priors and more efficient inference techniques.

I did my undergraduate studies in Molecular Life Sciences at the University of Hamburg, where I worked on phylogeny inference for quickly mutating virus strains with Andrew Torda. I then went to ETH Zürich to study Computational Biology and Bioinformatics (in a joint program with the University of Zürich), with a focus on systems biology and machine learning. My master's studies were suported by an ETH Excellence Scholarship. My master's thesis was about the application of deep learning to gene regulatory network inference under supervision of Manfred Claassen, for which I received the Willi Studer Prize. During my master's studies, I also spent some time in Jacob Hanna's group at the Weizmann Institute of Science, working on multiomics data analysis in stem cell research. Within my current PhD studies, I visited and worked with Stephan Mandt at the University of California in Irvine and Richard Turner at the University of Cambridge. Moreover, I completed internships at Disney Research Zürich, working with Romann Weber on deep learning for natural language understanding in the Machine Intelligence and Data Science team, and at Microsoft Research Cambridge, working with Katja Hofmann on uncertainty quantification in deep learning in the Game Intelligence team.


Publications

  1. PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
    Jonas Rothfuss, Vincent Fortuin, Andreas Krause
    arXiv, 2020
    [paper]

  2. GP-VAE: Deep Probabilistic Time Series Imputation
    Vincent Fortuin, Dmitry Baranchuk, Gunnar Rätsch, Stephan Mandt
    AISTATS, 2020
    [paper][code]

  3. Conservative Uncertainty Estimation By Fitting Prior Networks
    Kamil Ciosek, Vincent Fortuin, Ryota Tomioka, Katja Hofmann, Richard Turner
    ICLR, 2020
    [paper][code]

  4. Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations
    Andreas Kopf, Vincent Fortuin, Vignesh Ram Somnath, Manfred Claassen
    arXiv, 2019
    [paper]

  5. DPSOM: Deep Probabilistic Clustering with Self-Organizing Maps
    Laura Manduchi, Matthias Hüser, Gunnar Rätsch, Vincent Fortuin
    arXiv, 2019
    [paper][code]

  6. META^2: Memory-efficient taxonomic classification and abundance estimation for metagenomics with deep learning
    Andreas Georgiou, Vincent Fortuin, Harun Mustafa, Gunnar Rätsch
    arXiv, 2019
    [paper][code]

  7. MGP-AttTCN: An Interpretable Machine Learning Model for the Prediction of Sepsis
    Margherita Rosnati, Vincent Fortuin
    arXiv, 2019
    [paper]

  8. Meta-Learning Mean Functions for Gaussian Processes
    Vincent Fortuin, Heiko Strathmann, Gunnar Rätsch
    arXiv, 2019
    [paper]

  9. SOM-VAE: Interpretable Discrete Representation Learning on Time Series
    Vincent Fortuin, Matthias Hüser, Francesco Locatello, Heiko Strathmann, Gunnar Rätsch
    ICLR, 2019
    [paper][code]

  10. Scalable Gaussian Processes on Discrete Domains
    Vincent Fortuin, Gideon Dresdner, Heiko Strathmann, Gunnar Rätsch
    arXiv, 2018
    [paper]

  11. On the Connection between Neural Processes and Gaussian Processes with Deep Kernels
    Tim GJ Rudner, Vincent Fortuin, Yee Whye Teh, Yarin Gal
    Bayesian Deep Learning workshop at NeurIPS, 2018
    [paper]

  12. InspireMe: Learning Sequence Models for Stories
    Vincent Fortuin, Romann M Weber, Sasha Schriber, Diana Wotruba, Markus H Gross
    AAAI, 2018
    [paper]

  13. Supervised learning on synthetic data for reverse engineering gene regulatory networks from experimental time-series
    Stefan Ganscha, Vincent Fortuin, Max Horn, Eirini Arvaniti, Manfred Claassen
    bioRxiv, 2018
    [paper]

Invited Talks

Teaching

Service

Template Design by Aditya Grover.