Rodrigo Veiga
Postdoctoral Researcher
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 machine learning theory, particularly at the intersection between statistical physics, high-dimensional statistics, random matrix theory, and neural networks.
news
Feb 12, 2023 | Understanding the role of stochasticity in gradient-bases learning dynamics, as well as in achieving different global minima and how it is related to good generalization performances, is of most importance. Based on a continuous-time representation of stochastic gradient descent, in our new preprint Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features 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. We successfully apply the formalism to a high-dimensional linear regression model with random projections. Check it out! |
---|