Berthier, Raphaël

6 publications

ICLR 2025 Attention Layers Provably Solve Single-Location Regression Pierre Marion, Raphaël Berthier, Gérard Biau, Claire Boyer

ICML 2024 On the Minimal Degree Bias in Generalization on the Unseen for Non-Boolean Functions Denys Pushkin, Raphaël Berthier, Emmanuel Abbe

JMLR 2023 Incremental Learning in Diagonal Linear Networks Raphaël Berthier

NeurIPS 2023 Leveraging the Two-Timescale Regime to Demonstrate Convergence of Neural Networks Pierre Marion, Raphaël Berthier

NeurIPS 2021 Continuized Accelerations of Deterministic and Stochastic Gradient Descents, and of Gossip Algorithms Mathieu Even, Raphaël Berthier, Francis R. Bach, Nicolas Flammarion, Hadrien Hendrikx, Pierre Gaillard, Laurent Massoulié, Adrien Taylor

NeurIPS 2020 Tight Nonparametric Convergence Rates for Stochastic Gradient Descent Under the Noiseless Linear Model Raphaël Berthier, Francis R. Bach, Pierre Gaillard