Andreas M. Munk

PhD Computer Science, University of British Columbia

I am CEO at Evara AI Ltd. with a PhD in Computer Science, specializing in machine learning and artificial intelligence at the University of British Columbia, under the supervision of Frank Wood. My research areas were probabilistic programming, machine learning, and their practical applications. I am specifically interested in Bayesian inference and (conditional) generative modeling using deep learning and how these two frameworks may be combined by leveraging probabilistic programming.

I obtained my MSc. in Mathematical Modelling and Computation at the Technical University of Denmark (DTU), supervised by Morten Mørup. Prior to that I obtained my BSc in Earth and Space Physics and Engineering at DTU, supervised by Henrik Bruus.

news

Nov 20, 2020 To see how one may encourage Lipschitz continuity when training neural networks, see my presentation on Adversarial Lipschitz Regularization.
May 12, 2020 Presented Generative Modeling by Estimating Gradients of the Data Distribution in my reading group. Simply an awesome paper!
Oct 22, 2019 Launching website!

selected publications

    1. NeurIPS
      Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
      Baydin, Atilim Gunes, Shao, Lei, Bhimji, Wahid, Heinrich, Lukas, Naderiparizi, Saeid, Munk, Andreas, Liu, Jialin, Gram-Hansen, Bradley, Louppe, Gilles, Meadows, Lawrence, Torr, Philip, Lee, Victor, Cranmer, Kyle, Prabhat, Mr., and Wood, Frank
      2019
    2. Deep Probabilistic Surrogate Networks for Universal Simulator Approximation
      Munk, Andreas, Ścibior, Adam, Baydin, Atılım Güneş, Stewart, Andrew, Fernlund, Goran, Poursartip, Anoush, and Wood, Frank
      arXiv:1910.11950 [cs, stat] 2019
    1. ICASSP
      Semi-Supervised Sleep-Stage Scoring Based on Single Channel EEG
      Munk, A. M., Olesen, K. V., Gangstad, S. W., and Hansen, L. K.
      In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018