Items where Author is "Stich, Sebastian U."

Up a level
Export as [feed] Atom [feed] RSS 1.0 [feed] RSS 2.0
Group by: Item Type | No Grouping
Number of items: 12.

Jiang, Xiaowen and Stich, Sebastian U.
(2023) Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction.
In: Conference on Neural Information Processing Systems, 11.12.2023-16.12.2023, New Orleans, USA.
Conference: NeurIPS Conference on Neural Information Processing Systems

Koloskova, Anastasia and Hendrikx, Hadrien and Stich, Sebastian U.
(2023) Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees.
In: International Conference on Machine Learning (ICML), Honolulu, USA.
Conference: ICML International Conference on Machine Learning

Mohtashami, Amirkeivan and Jaggi, Martin and Stich, Sebastian U.
(2023) Special Properties of Gradient Descent with Large Learning Rates.
In: International Conference on Machine Learning (ICML), Honolulu, USA.
Conference: ICML International Conference on Machine Learning

Bo, Li and Schmidt, Mikkel N. and Alstrøm, Tommy S. and Stich, Sebastian U.
(2023) On the effectiveness of partial variance reduction in federated learning with heterogeneous data.
In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada.
Conference: CVPR IEEE Conference on Computer Vision and Pattern Recognition

Horváth, Samuel and Kovalev, Dmitry and Mishchenko, Konstantin and Richtárik, Peter and Stich, Sebastian U.
(2023) Stochastic distributed learning with gradient quantization and double-variance reduction.
Optimization Methods and Software, 38 (1). pp. 91-106.

Dodwadmath, Akshay and Stich, Sebastian U.
(2022) Preserving privacy with PATE for heterogeneous data.
In: NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications, 28.11.2022-9.12.2022, New Orleans, USA.
Conference: NeurIPS-W Workshop on Neural Information Processing Systems

Beznosikov, Aleksandr and Dvurechensky, Pavel and Koloskova, Anastasia and Samokhin, Valentin and Stich, Sebastian U. and Gasnikov, Alexander
(2022) Decentralized Local Stochastic Extra-Gradient for Variational Inequalities.
In: NeurIPS, 28.11.2022-9.12.2022, New Orleans, USA.
Conference: NeurIPS Conference on Neural Information Processing Systems

Koloskova, Anastasia and Stich, Sebastian U. and Jaggi, Martin
(2022) Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning.
In: NeurIPS, 28.11.2022-9.12.2022, New Orleans, USA.
Conference: NeurIPS Conference on Neural Information Processing Systems

Wang, Hui-Po and Stich, Sebastian U. and He, Yang and Fritz, Mario
(2022) ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training.
In: International Conference on Machine Learning (ICML), 19.7.2022 - 21.7.2022, Baltimore, USA.
Conference: ICML International Conference on Machine Learning

Mishchenko, Konstantin and Malinovsky, Grigory and Stich, Sebastian U. and Richtarik, Peter
(2022) ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!
In: International Conference on Machine Learning (ICML).
Conference: ICML International Conference on Machine Learning

Mohtashami, Amirkeivan and Jaggi, Martin and Stich, Sebastian U.
(2022) Masked Training of Neural Networks with Partial Gradients.
In: AISTATS 2022, 28 Mar - 30 Mar 2022, online.
Conference: AISTATS International Conference on Artificial Intelligence and Statistics
(In Press)

Liu, Yehao and Pagliardini, Matteo and Chavdarova, Tatjana and Stich, Sebastian U.
(2021) The Peril of Popular Deep Learning Uncertainty Estimation Methods.
In: Bayesian Deep Learning Workshop at NeurIPS 2021, 14.12.2021, online.
Conference: BDL Bayesian Deep Learning Workshop

This list was generated on Sat Dec 21 17:00:16 2024 CET.
CISPA is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.