Rodrigo Veiga

prof_pic_optimized.jpg

I am an Assistant Professor in the School of Mathematical Sciences at the University of Nottingham. My research lies broadly in machine learning theory, with a particular focus on high-dimensional problems at the intersection of machine learning, statistical inference, and statistical mechanics.

news

Sep 24, 2026 Our paper Information-Geometric Forward Policy Training in GFlowNets was accepted to the NeurIPS 2026 Main Conference.
Jan 22, 2026 Our paper Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves was accepted as a Spotlight at AISTATS 2026.
Sep 1, 2025 I am glad to share that I will be starting this September as an Assistant Professor in the School of Mathematical Sciences at the University of Nottingham.

selected publications

  1. gflownet_geometry.png
    Information-Geometric Forward Policy Training in GFlowNets
    Yordan Raykov, and Rodrigo Veiga
    Accepted to the NeurIPS 2026 Main Conference.
  2. diff_phdiag.jpg
    Denoising Score Matching with Random Features: Insights on Diffusion Models From Precise Learning Curves
    Anand Jerry George, Rodrigo Veiga, and Nicolas Macris
    In Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, May 2026
    Spotlight. Republished in Journal of Statistical Mechanics: Theory and Experiment.