Sebastian U. Stich

Publication Activity (10 Years)

Years Active: 2009-2024
Publications (10 Years): 104

Top Venues

CoRR

ICML

NeurIPS

ICLR

Publications

Bo Li, Xiaowen Jiang, Mikkel N. Schmidt, Tommy Sonne Alstrøm, Sebastian U. Stich
An improved analysis of per-sample and per-update clipping in federated learning. ICLR (2024)
Bo Li, Yasin Esfandiari, Mikkel N. Schmidt, Tommy Sonne Alstrøm, Sebastian U. Stich
Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity. Trans. Mach. Learn. Res. 2024 (2024)
Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich
Federated Optimization with Doubly Regularized Drift Correction. CoRR (2024)
Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich
Stabilized Proximal-Point Methods for Federated Optimization. CoRR (2024)
Rustem Islamov, Yuan Gao, Sebastian U. Stich
Near Optimal Decentralized Optimization with Compression and Momentum Tracking. CoRR (2024)
Siqi Zhang, Sayantan Choudhury, Sebastian U. Stich, Nicolas Loizou
Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates. ICLR (2024)
Kumar Kshitij Patel, Margalit Glasgow, Ali Zindari, Lingxiao Wang, Sebastian U. Stich, Ziheng Cheng, Nirmit Joshi, Nathan Srebro
The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication. COLT (2024)
Yuan Gao, Rustem Islamov, Sebastian U. Stich
EControl: Fast Distributed Optimization with Compression and Error Control. ICLR (2024)
Kumar Kshitij Patel, Margalit Glasgow, Ali Zindari, Lingxiao Wang, Sebastian U. Stich, Ziheng Cheng, Nirmit Joshi, Nathan Srebro
The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication. CoRR (2024)
Yuan Gao, Anton Rodomanov, Sebastian U. Stich
Non-Convex Stochastic Composite Optimization with Polyak Momentum. CoRR (2024)
Bo Li, Yasin Esfandiari, Mikkel N. Schmidt, Tommy S. Alstrøm, Sebastian U. Stich
Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity. CoRR (2023)
Bo Li, Mikkel N. Schmidt, Tommy S. Alstrøm, Sebastian U. Stich
On the Effectiveness of Partial Variance Reduction in Federated Learning with Heterogeneous Data. CVPR (2023)
Xiaowen Jiang, Sebastian U. Stich
Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction. CoRR (2023)
Anastasia Koloskova, Nikita Doikov, Sebastian U. Stich, Martin Jaggi
Shuffle SGD is Always Better than SGD: Improved Analysis of SGD with Arbitrary Data Orders. CoRR (2023)
Sohom Mukherjee, Nicolas Loizou, Sebastian U. Stich
Locally Adaptive Federated Learning via Stochastic Polyak Stepsizes. CoRR (2023)
Yue Liu, Tao Lin, Anastasia Koloskova, Sebastian U. Stich
Decentralized Gradient Tracking with Local Steps. CoRR (2023)
Xiaowen Jiang, Sebastian U. Stich
Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction. NeurIPS (2023)
Anastasia Koloskova, Hadrien Hendrikx, Sebastian U. Stich
Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees. CoRR (2023)
Siqi Zhang, Sayantan Choudhury, Sebastian U. Stich, Nicolas Loizou
Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates. CoRR (2023)
Anastasia Koloskova, Hadrien Hendrikx, Sebastian U. Stich
Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees. ICML (2023)
Samuel Horváth, Dmitry Kovalev, Konstantin Mishchenko, Peter Richtárik, Sebastian U. Stich
Stochastic distributed learning with gradient quantization and double-variance reduction. Optim. Methods Softw. 38 (1) (2023)
Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich
Special Properties of Gradient Descent with Large Learning Rates. ICML (2023)
Aleksandr Beznosikov, Pavel E. Dvurechensky, Anastasia Koloskova, Valentin Samokhin, Sebastian U. Stich, Alexander V. Gasnikov
Decentralized Local Stochastic Extra-Gradient for Variational Inequalities. NeurIPS (2022)
Hui-Po Wang, Sebastian U. Stich, Yang He, Mario Fritz
ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training. ICML (2022)
Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich
On Avoiding Local Minima Using Gradient Descent With Large Learning Rates. CoRR (2022)
Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning. NeurIPS (2022)
Harsh Vardhan, Sebastian U. Stich
Tackling benign nonconvexity with smoothing and stochastic gradients. CoRR (2022)
Yatin Dandi, Anastasia Koloskova, Martin Jaggi, Sebastian U. Stich
Data-heterogeneity-aware Mixing for Decentralized Learning. CoRR (2022)
Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning. CoRR (2022)
Anastasia Koloskova, Tao Lin, Sebastian U. Stich
An Improved Analysis of Gradient Tracking for Decentralized Machine Learning. CoRR (2022)
Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich
Masked Training of Neural Networks with Partial Gradients. AISTATS (2022)
Amirkeivan Mohtashami, Sebastian U. Stich, Martin Jaggi
Characterizing & Finding Good Data Orderings for Fast Convergence of Sequential Gradient Methods. CoRR (2022)
Bo Li, Mikkel N. Schmidt, Tommy S. Alstrøm, Sebastian U. Stich
Partial Variance Reduction improves Non-Convex Federated learning on heterogeneous data. CoRR (2022)
Oguz Kaan Yüksel, Sebastian U. Stich, Martin Jaggi, Tatjana Chavdarova
Semantic Perturbations with Normalizing Flows for Improved Generalization. ICCV (2021)
Jianyu Wang, Zachary Charles, Zheng Xu, Gauri Joshi, H. Brendan McMahan, Blaise Agüera y Arcas, Maruan Al-Shedivat, Galen Andrew, Salman Avestimehr, Katharine Daly, Deepesh Data, Suhas N. Diggavi, Hubert Eichner, Advait Gadhikar, Zachary Garrett, Antonious M. Girgis, Filip Hanzely, Andrew Hard, Chaoyang He, Samuel Horvath, Zhouyuan Huo, Alex Ingerman, Martin Jaggi, Tara Javidi, Peter Kairouz, Satyen Kale, Sai Praneeth Karimireddy, Jakub Konecný, Sanmi Koyejo, Tian Li, Luyang Liu, Mehryar Mohri, Hang Qi, Sashank J. Reddi, Peter Richtárik, Karan Singhal, Virginia Smith, Mahdi Soltanolkotabi, Weikang Song, Ananda Theertha Suresh, Sebastian U. Stich, Ameet Talwalkar, Hongyi Wang, Blake E. Woodworth, Shanshan Wu, Felix X. Yu, Honglin Yuan, Manzil Zaheer, Mi Zhang, Tong Zhang, Chunxiang Zheng, Chen Zhu, Wennan Zhu
A Field Guide to Federated Optimization. CoRR (2021)
Dmitry Kovalev, Anastasia Koloskova, Martin Jaggi, Peter Richtárik, Sebastian U. Stich
A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free! AISTATS (2021)
El Mahdi Chayti, Sai Praneeth Karimireddy, Sebastian U. Stich, Nicolas Flammarion, Martin Jaggi
Linear Speedup in Personalized Collaborative Learning. CoRR (2021)
Hossein Shokri Ghadikolaei, Sebastian U. Stich, Martin Jaggi
LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads. AISTATS (2021)
Hui-Po Wang, Sebastian U. Stich, Yang He, Mario Fritz
ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training. CoRR (2021)
Aleksandr Beznosikov, Pavel E. Dvurechensky, Anastasia Koloskova, Valentin Samokhin, Sebastian U. Stich, Alexander V. Gasnikov
Decentralized Local Stochastic Extra-Gradient for Variational Inequalities. CoRR (2021)
Oguz Kaan Yüksel, Sebastian U. Stich, Martin Jaggi, Tatjana Chavdarova
Semantic Perturbations with Normalizing Flows for Improved Generalization. CoRR (2021)
Tao Lin, Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi
Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data. ICML (2021)
Sebastian U. Stich, Amirkeivan Mohtashami, Martin Jaggi
Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates. CoRR (2021)
Thijs Vogels, Lie He, Anastasia Koloskova, Tao Lin, Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi
RelaySum for Decentralized Deep Learning on Heterogeneous Data. CoRR (2021)
Yehao Liu, Matteo Pagliardini, Tatjana Chavdarova, Sebastian U. Stich
The Peril of Popular Deep Learning Uncertainty Estimation Methods. CoRR (2021)
Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich
Simultaneous Training of Partially Masked Neural Networks. CoRR (2021)
Thijs Vogels, Lie He, Anastasia Koloskova, Sai Praneeth Karimireddy, Tao Lin, Sebastian U. Stich, Martin Jaggi
RelaySum for Decentralized Deep Learning on Heterogeneous Data. NeurIPS (2021)
Lingjing Kong, Tao Lin, Anastasia Koloskova, Martin Jaggi, Sebastian U. Stich
Consensus Control for Decentralized Deep Learning. CoRR (2021)
Lingjing Kong, Tao Lin, Anastasia Koloskova, Martin Jaggi, Sebastian U. Stich
Consensus Control for Decentralized Deep Learning. ICML (2021)
Sebastian U. Stich, Amirkeivan Mohtashami, Martin Jaggi
Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates. AISTATS (2021)
Tatjana Chavdarova, Matteo Pagliardini, Sebastian U. Stich, François Fleuret, Martin Jaggi
Taming GANs with Lookahead-Minmax. ICLR (2021)
Tao Lin, Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi
Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data. CoRR (2021)
Sebastian Bischoff, Stephan Günnemann, Martin Jaggi, Sebastian U. Stich
On Second-order Optimization Methods for Federated Learning. CoRR (2021)
Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale, Mehryar Mohri, Sashank J. Reddi, Sebastian U. Stich, Ananda Theertha Suresh
Breaking the centralized barrier for cross-device federated learning. NeurIPS (2021)
Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista A. Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Hubert Eichner, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaïd Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konecný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Hang Qi, Daniel Ramage, Ramesh Raskar, Mariana Raykova, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
Advances and Open Problems in Federated Learning. Found. Trends Mach. Learn. 14 (1-2) (2021)
Anastasia Koloskova, Tao Lin, Sebastian U. Stich
An Improved Analysis of Gradient Tracking for Decentralized Machine Learning. NeurIPS (2021)
Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi
Extrapolation for Large-batch Training in Deep Learning. ICML (2020)
Tao Lin, Sebastian U. Stich, Kumar Kshitij Patel, Martin Jaggi
Don't Use Large Mini-batches, Use Local SGD. ICLR (2020)
Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi
Ensemble Distillation for Robust Model Fusion in Federated Learning. NeurIPS (2020)
Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi
Ensemble Distillation for Robust Model Fusion in Federated Learning. CoRR (2020)
Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi
Extrapolation for Large-batch Training in Deep Learning. CoRR (2020)
Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale, Mehryar Mohri, Sashank J. Reddi, Sebastian U. Stich, Ananda Theertha Suresh
Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning. CoRR (2020)
Blake E. Woodworth, Kumar Kshitij Patel, Sebastian U. Stich, Zhen Dai, Brian Bullins, H. Brendan McMahan, Ohad Shamir, Nathan Srebro
Is Local SGD Better than Minibatch SGD? ICML (2020)
Tao Lin, Sebastian U. Stich, Luis Barba, Daniil Dmitriev, Martin Jaggi
Dynamic Model Pruning with Feedback. CoRR (2020)
Anastasia Koloskova, Nicolas Loizou, Sadra Boreiri, Martin Jaggi, Sebastian U. Stich
A Unified Theory of Decentralized SGD with Changing Topology and Local Updates. ICML (2020)
Dmitry Kovalev, Anastasia Koloskova, Martin Jaggi, Peter Richtárik, Sebastian U. Stich
A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free! CoRR (2020)
Anastasia Koloskova, Nicolas Loizou, Sadra Boreiri, Martin Jaggi, Sebastian U. Stich
A Unified Theory of Decentralized SGD with Changing Topology and Local Updates. CoRR (2020)
Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank J. Reddi, Sebastian U. Stich, Ananda Theertha Suresh
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning. ICML (2020)
Anastasia Koloskova, Tao Lin, Sebastian U. Stich, Martin Jaggi
Decentralized Deep Learning with Arbitrary Communication Compression. ICLR (2020)
Sebastian U. Stich
On Communication Compression for Distributed Optimization on Heterogeneous Data. CoRR (2020)
Tao Lin, Sebastian U. Stich, Luis Barba, Daniil Dmitriev, Martin Jaggi
Dynamic Model Pruning with Feedback. ICLR (2020)
Blake E. Woodworth, Kumar Kshitij Patel, Sebastian U. Stich, Zhen Dai, Brian Bullins, H. Brendan McMahan, Ohad Shamir, Nathan Srebro
Is Local SGD Better than Minibatch SGD? CoRR (2020)
Ahmad Ajalloeian, Sebastian U. Stich
Analysis of SGD with Biased Gradient Estimators. CoRR (2020)
Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication. ICML (2019)
Sebastian U. Stich
Unified Optimal Analysis of the (Stochastic) Gradient Method. CoRR (2019)
Sebastian U. Stich, Sai Praneeth Karimireddy
The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication. CoRR (2019)
Sai Praneeth Karimireddy, Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
Efficient Greedy Coordinate Descent for Composite Problems. AISTATS (2019)
Anastasia Koloskova, Tao Lin, Sebastian U. Stich, Martin Jaggi
Decentralized Deep Learning with Arbitrary Communication Compression. CoRR (2019)
Sai Praneeth Karimireddy, Quentin Rebjock, Sebastian U. Stich, Martin Jaggi
Error Feedback Fixes SignSGD and other Gradient Compression Schemes. ICML (2019)
Sebastian U. Stich
Local SGD Converges Fast and Communicates Little. ICLR (Poster) (2019)
Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista A. Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaïd Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konecný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
Advances and Open Problems in Federated Learning. CoRR (2019)
Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication. CoRR (2019)
Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank J. Reddi, Sebastian U. Stich, Ananda Theertha Suresh
SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning. CoRR (2019)
Sai Praneeth Karimireddy, Quentin Rebjock, Sebastian U. Stich, Martin Jaggi
Error Feedback Fixes SignSGD and other Gradient Compression Schemes. CoRR (2019)
Sai Praneeth Karimireddy, Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
Efficient Greedy Coordinate Descent for Composite Problems. CoRR (2018)
Francesco Locatello, Anant Raj, Sai Praneeth Karimireddy, Gunnar Rätsch, Bernhard Schölkopf, Sebastian U. Stich, Martin Jaggi
On Matching Pursuit and Coordinate Descent. ICML (2018)
Anant Raj, Sebastian U. Stich
SVRG meets SAGA: k-SVRG - A Tale of Limited Memory. CoRR (2018)
Francesco Locatello, Anant Raj, Sai Praneeth Karimireddy, Gunnar Rätsch, Bernhard Schölkopf, Sebastian U. Stich, Martin Jaggi
Revisiting First-Order Convex Optimization Over Linear Spaces. CoRR (2018)
Sebastian U. Stich
Local SGD Converges Fast and Communicates Little. CoRR (2018)
Sebastian U. Stich, Jean-Baptiste Cordonnier, Martin Jaggi
Sparsified SGD with Memory. CoRR (2018)
Tao Lin, Sebastian U. Stich, Martin Jaggi
Don't Use Large Mini-Batches, Use Local SGD. CoRR (2018)
Robert M. Gower, Filip Hanzely, Peter Richtárik, Sebastian U. Stich
Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization. NeurIPS (2018)
Robert M. Gower, Filip Hanzely, Peter Richtárik, Sebastian U. Stich
Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization. CoRR (2018)
Sai Praneeth Reddy Karimireddy, Sebastian U. Stich, Martin Jaggi
Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems. AISTATS (2018)
Sebastian U. Stich, Jean-Baptiste Cordonnier, Martin Jaggi
Sparsified SGD with Memory. NeurIPS (2018)
Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi
Global linear convergence of Newton's method without strong-convexity or Lipschitz gradients. CoRR (2018)
Radoslav Fulek, Hossein Nassajian Mojarrad, Márton Naszódi, József Solymosi, Sebastian U. Stich, May Szedlák
On the existence of ordinary triangles. Comput. Geom. 66 (2017)
Yurii E. Nesterov, Sebastian U. Stich
Efficiency of the Accelerated Coordinate Descent Method on Structured Optimization Problems. SIAM J. Optim. 27 (1) (2017)
Sebastian U. Stich, Anant Raj, Martin Jaggi
Safe Adaptive Importance Sampling. CoRR (2017)
Sebastian U. Stich, Anant Raj, Martin Jaggi
Approximate Steepest Coordinate Descent. ICML (2017)

Sebastian U. Stich.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Sebastian U. Stich