Showing stat.MLShow all
2 papers · 1 filter
stat.ML2025
Convergence and concentration properties of constant step-size SGD through Markov chains
Ibrahim Merad, Stéphane Gaïffas
We consider the optimization of a smooth and strongly convex objective using constant step-size stochastic gradient descent (SGD) and study its properties through the prism of Mark…
stat.ML2024
Robust Stochastic Optimization via Gradient Quantile Clipping
Ibrahim Merad, Stéphane Gaïffas
We introduce a clipping strategy for Stochastic Gradient Descent (SGD) which uses quantiles of the gradient norm as clipping thresholds. We prove that this new strategy provides a…