Send email Copy Email Address

Email

Address

Im Oberen Werk 1
66386 St. Ingbert (Germany)

Further Information

Short Bio

Dr. Sebastian Stich is tenured faculty at CISPA. Since June 2020 he is a member of the European Lab for Learning and Intelligent Systems. From December 1st 2016 to November 30th 2021, he worked as a research scientist at EPFL, hosted by Prof. Martin JaggiMachine Learning and Optimization Laboratory (MLO). From November 1st 2014 to October 31st 2016, he worked with Prof. Yurii Nesterov and Prof. François Glineur at the Center for Operations Research and Econometrics (CORE) and the ICTEAM. From September 15th 2010 to September 30th 2014, he was a PHD student in Prof. Emo Welzl's research group, supervised by Prof. Bernd Gärtner and Christian Lorenz Müller. And from September 2005 to March 2010 he did his Bachelor and Master in Mathematics at ETH Zurich.

CV: Last stations

Since 2025
Tenured Faculty at CISPA Helmholtz Center for Information Security
Since 2021
Tenure-Track Faculty at CISPA Helmholtz Center for Information Security
2016 - 2021
Research scientist at EPFL
2014 - 2016
Center for Operations Research and Econometrics (CORE) and the ICTEAM
2010 - 2014
PHD student at ETH Zurich

Publications by Sebastian Stich

Year 2024

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS) Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction

Conference / Medium

International Conference on Learning Representations (ICLR)

Article

Transactions on Machine Learning Research Locally Adaptive Federated Learning

Conference / Medium

International Conference on Machine Learning (ICML) Federated Optimization with Doubly Regularized Drift Correction

Conference / Medium

International Conference on Machine Learning (ICML) Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions

Conference / Medium

International Conference on Machine Learning (ICML) On Convergence of Incremental Gradient for Non-convex Smooth Functions

Conference / Medium

International Conference on Machine Learning (ICML) Non-Convex Stochastic Composite Optimization with Polyak Momentum

Conference / Medium

Conference on Learning Theory (COLT) The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication

Conference / Medium

International Conference on Learning Representations (ICLR) An improved analysis of per-sample and per-update clipping in federated learning

Conference / Medium

International Conference on Learning Representations (ICLR) Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates