Fabian Schaipp

Postdoc, INRIA

Joined

January 2023

Names

Fabian Schaipp (Preferred)

Emails

****@gmail.com (Confirmed)

****@tum.de (Confirmed)

****@inria.fr (Confirmed)

Personal Links

DBLP

ORCID

Career & Education History

Postdoc

INRIA (inria.fr)

2024 – Present

PhD student

Mathematics, Technische Universität München (tum.de)

2020 – 2024

Advisors, Relations & Conflicts

Postdoc Advisor

Francis Bach

2024 – Present

Postdoc Advisor

Adrien Taylor

2024 – Present

Postdoc Advisor

Umut Simsekli

2024 – Present

PhD Advisor

Michael Ulbrich

2020 – 2024

Expertise

optimization

Present

deep learning

Present

sparse network estimation

Present

Publications

The surprising agreement between convex optimization theory and learning-rate scheduling for large model training
Adrien Taylor, Fabian Schaipp, Alexander Hägele, Umut Simsekli, Francis Bach
- International conference on Machine Learning (ICML)
- Readers: Everyone
Optimization Benchmark for Diffusion Models on Dynamical Systems
Fabian Schaipp
- EurIPS 2025 Workshop PriGM
- Readers: Everyone
Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation
Robert M. Gower, Guillaume Garrigos, Nicolas Loizou, Konstantin Mishchenko, Dimitris Oikonomou, Fabian Schaipp
- Submitted to ICLR 2026
- Readers: Everyone
Tracking the Median of Gradients with a Stochastic Proximal Point Method
Fabian Schaipp, Guillaume Garrigos, Umut Simsekli, Robert M. Gower
- Accepted by TMLR
- Readers: Everyone
Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation
Robert M. Gower, Guillaume Garrigos, Nicolas Loizou, Konstantin Mishchenko, Dimitris Oikonomou, Fabian Schaipp
- Submitted to ICML 2025
- Readers: Everyone
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
- ICML 2025 poster
- Readers: Everyone
A Semismooth Newton Stochastic Proximal Point Algorithm with Variance Reduction
Andre Milzarek, Fabian Schaipp, Michael Ulbrich
- SIAM J. Optim. 2024
- Readers: Everyone
MoMo: Momentum Models for Adaptive Learning Rates
Fabian Schaipp, Ruben Ohana, Michael Eickenberg, Aaron Defazio, Robert M. Gower
- ICML 2024 Poster
- Readers: Everyone
Topics in Stochastic Optimization: Learning with Implicit and Adaptive Steps (Implizite und Adaptive Methoden der Stochastischen Optimierung für Machine Learning)
Fabian Schaipp
- undefined 2024
- Readers: Everyone
SGD with Clipping is Secretly Estimating the Median Gradient
Fabian Schaipp, Guillaume Garrigos, Umut Simsekli, Robert M. Gower
- CoRR 2024
- Readers: Everyone

View all 18 publications

Fabian Schaipp

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Co-Authors