3 papers
math.NA2026
Minimax-Optimal Early Stopping for Continuous-Time SGD via the Discrepancy Principle
Tim Jahn, Loucas Pillaud-Vivien, Adrien Schertzer
We study early stopping for a continuous-time model of stochastic gradient descent (SGD) in ill-posed linear inverse problems. We consider an a posteriori stopping rule based on th…
cs.LG2025
Joint Learning in the Gaussian Single Index Model
Loucas Pillaud-Vivien, Adrien Schertzer
We consider the problem of jointly learning a one-dimensional projection and a univariate function in high-dimensional Gaussian models. Specifically, we study predictors of the for…
cs.LG2024
Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent
Adrien Schertzer, Loucas Pillaud-Vivien
We study the dynamics of a continuous-time model of the Stochastic Gradient Descent (SGD) for the least-square problem. Indeed, pursuing the work of Li et al. (2019), we analyze St…