Adrián Javaloy

University of Edinburgh

prof-pic.jpg

I am a postdoc at the April lab working with Dr. Antonio Vergari on robust and reliable probabilistic machine learning approaches.

I completed my PhD at the Probabilistic Machine Learning group working with Prof. Isabel Valera at Saarland University. Before that, I worked at the Max Planck Institute for Intelligent Systems in Tübingen at the Empirical Inference department and the Probabilistic Machine Learning group.

My research focuses on developing methods that are reliable, principled, and efficient. Loosely, I introduce inductive biases to models such that they comply with our expectations on how they should behave in the wild. My ultimate goal is to conduct interesting and principled research to better understand machine learning models and ease their deployment in the real-world.

news

May 07, 2026 🎉 An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale will be at ICML 2026
Jan 25, 2026 🎉 How to Square Tensor Networks and Circuits Without Squaring Them will be at ICLR 2026
Oct 24, 2025 💡 DeCaFlow: A deconfounding causal generative model is now a spotlight at NeurIPS 2025
Mar 11, 2025 🎓 My dissertation was awarded summa cum laude!
Oct 04, 2024 🙈 I have joined the april lab as a postdoc at the Universty of Edimburgh

selected publications

  1. An Embarrasingly Simple Way to Optimize Orthogonal Matrices at Scale
    Adrián Javaloy and Antonio Vergari
    In Forty-third International Conference on Machine Learning, 2026
  2. How to Square Tensor Networks and Circuits Without Squaring Them
    Lorenzo Loconte, Adrián Javaloy, and Antonio Vergari
    In The Fourteenth International Conference on Learning Representations, ICLR 2026, 2026
  3. Preprint
    COPA: Comparing the incomparable in multi-objective model evaluation
    Adrián Javaloy, Antonio Vergari, and Isabel Valera
    arXiv preprint arXiv:2503.14321, 2025
  4. DeCaFlow: A deconfounding causal generative model
    Alejandro Almodóvar*, Adrián Javaloy*, Juan Parras, and 2 more authors
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
  5. Dissertation
    Meet my expectations: on the interplay of trustworthiness and deep learning optimization
    Adrián Javaloy
    2024
  6. Causal normalizing flows: from theory to practice
    Adrián Javaloy, Pablo Sánchez-Martín, and Isabel Valera
    In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, 2023