Rodrigo Veiga

Postdoctoral Researcher

prof_pic.jpg

I am a Postdoctoral Researcher at the Lab for Statistical Mechanics of Inference in Large Systems (SMILS) at the École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland. My research focus is on intersection between machine learning and statistical mechanics.

news

Jul 23, 2024 Together with my colleague Anastasia Remizova, I will be presenting our work Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features on the Poster Session 1 at ICML, Hall C 4-9, from 11:30 am to 1 pm (CEST). We will be next to poster #1901. Come and have a chat with us!
May 20, 2024 It was a pleasure to visit ICTP in Trieste, Italy, to attend and give a talk at the Youth in High Dimensions: Recent Progress in Machine Learning, High-Dimensional Statistics and Inference conference.
May 2, 2024 Our paper Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features, in collaboration with Anastasia Remizova and Nicolas Macris, has been accepted to ICML 2024. See you in Vienna in July!
Apr 15, 2024 This week, I have the pleasure of attending and giving a talk at the From Theory to Practice workshop at the AIMS Research and Innovation Centre in Kigali, Rwanda.
Feb 12, 2024 Understanding the role of stochasticity in gradient-based learning dynamics and in achieving different global minima and how it is related to good generalization performances is of most importance. In our new preprint, Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features, in collaboration with Anastasia Remizova and Nicolas Macris, we construct a path-integral framework to compute the difference between pure gradient flow and stochastic gradient flow trajectories in the limit of small learning rate. Check it out!

selected publications

  1. sgf_fig04.jpg
    Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features
    Rodrigo Veiga, Anastasia Remizova, and Nicolas Macris
    In Proceedings of the 41st International Conference on Machine Learning, 21–27 jul 2024
  2. arXiv_fig01_image.jpg
    Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks
    Rodrigo Veiga, Ludovic Stephan, Bruno Loureiro, and 2 more authors
    In Advances in Neural Information Processing Systems, 21–27 jul 2022