Schaipp, Fabian

5 publications

ICML 2025 The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training Fabian Schaipp, Alexander Hägele, Adrien Taylor, Umut Simsekli, Francis Bach

TMLR 2025 Tracking the Median of Gradients with a Stochastic Proximal Point Method Fabian Schaipp, Guillaume Garrigos, Umut Simsekli, Robert M. Gower

ICML 2024 MoMo: Momentum Models for Adaptive Learning Rates Fabian Schaipp, Ruben Ohana, Michael Eickenberg, Aaron Defazio, Robert M. Gower

TMLR 2023 A Stochastic Proximal Polyak Step Size Fabian Schaipp, Robert M. Gower, Michael Ulbrich

NeurIPSW 2023 Robust Gradient Estimation in the Presence of Heavy-Tailed Noise Fabian Schaipp, Umut Simsekli, Robert M. Gower