Ignacio Peis

Postdoctoral Researcher


I am a postdoctoral researcher at the Section for Cognitive Systems, in Technical University of Denmark (DTU). I work within Jes Frellsen’s group, where we embark on a range of fascinating projects.

Research   I am interested in the connection between Deep Learning and Probabilistic Modelling. My current research lies in creating more expressive generative models, increasing their robustness (e.g. dealing with mixed-type data or missing data) and developing better inference methods. My work has been applied to several fields, like Neuroscience or Psychiatry.

Previously   I completed my PhD in Probabilistic Machine Learning at Universidad Carlos III de Madrid (UC3M), where I was supervised by Prof. Antonio Artés-Rodríguez and Dr. Pablo M. Olmos from the Signal Processing Group. Previously, I was a research intern at the Machine Learning Group in the Department of the Engineering, University of Cambridge where I worked with Prof. José Miguel Hernández-Lobato. I obtained two MSc degrees in Telecommunications Engineering and Signal Processing from UC3M, and my BSc degree in Telecommunications Engineering from Universidad de Granada (UGR).

latest news [all]

Dec 20, 2023 I will give a talk about my recent research at the first edition of the Andaluz.IA forum, that will be held on Wednesday 20th December 2023 at Pablo de Olavide University in Sevilla, Spain. Find here a link to the slides.
Dec 1, 2023 I have received the Outstanding Thesis Award for my PhD thesis!
Oct 1, 2023 Hi from Copenhagen! I started a Postdoctoral position with Jes Frellsen’s group at the Technical University of Denmark (DTU), Denmark. Thanks again to the Danish Data Science Academy (DDSA) and to the Novo Nordisk Foundation for awarding my research project!
Sep 22, 2023 I successfully defended my PhD thesis! What an enriching experience. Thank you all for your support. You can find here the [manuscript] and the [slides].
Jul 24, 2023 Aloha ICML23! We’re presenting our paper! Come to see our poster and chat with us at Exhibit Hall 1 #432 on Thursday 27 Jul at 10:30 am (Poster Session 5)! ⏱️ We’ll explain to you how to learn distributions of functions using a VAE framework!

selected publications

  1. vamoh.png
    Variational Mixture of HyperGenerators for Learning Distributions Over Functions
    Batuhan KoyuncuPablo Sanchez-MartinIgnacio Peis, and 2 more authors
    In Proceedings of the 40th International Conference on Machine Learning, 2023
  2. hhvaem.png
    Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo
    Ignacio PeisChao Ma, and José Miguel Hernández-Lobato
    In Advances in Neural Information Processing Systems 35, 2022
  3. ugvae.png
    Unsupervised learning of global factors in deep generative models
    Pattern Recognition, 2022