← Authors

Sebastian U Stich

29 papers · 2017–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (12) πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (8) πŸ—ΊοΈ Taxonomy Completionist (17) 🀝 Dynamic Duo (11) πŸ‘‘ Triple Crown πŸ”₯ Unstoppable (6) πŸ’Ž Century Club (29) πŸ—ƒοΈ Keyword Collector (59) ⚑ Prolific Year (9)

Conferences

NIPS (11) ICLR (8) ICML (8) AISTATS (1) COLT (1)

Top co-authors

Martin Jaggi (11) Anton Rodomanov (6) Xiaowen Jiang (5) Anastasiia Koloskova (4) Tao LIN (3) Yuan Gao (3) Sai Praneeth Karimireddy (2) Ali Zindari (2) Nikita Doikov (2) Rustem Islamov (2)

Keywords

distributed learning (6) stochastic optimization (5) federated learning (5) stochastic gradient descent (5) distributed optimization (3) decentralized optimization (2) variance reduction (2) decentralized learning (2) convergence rate (2) communication efficiency (2) convergence guarantee (2) game theory (1) deep learning (1) model fusion (1) convex optimization (1) distributed training (1) communication complexity (1) coordinate descent (1) knowledge distillation (1) importance sampling (1)

Papers

Scalable Decentralized Learning with Teleportation ICLR 2025
Decoupled SGDA for Games with Intermittent Strategy Communication ICML 2025
Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization ICML 2025
Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis AISTATS 2025
Towards Faster Decentralized Stochastic Optimization with Communication Compression ICLR 2025
Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods ICLR 2025
EControl: Fast Distributed Optimization with Compression and Error Control ICLR 2024
Federated Optimization with Doubly Regularized Drift Correction ICML 2024
Non-convex Stochastic Composite Optimization with Polyak Momentum ICML 2024
Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions ICML 2024
An improved analysis of per-sample and per-update clipping in federated learning ICLR 2024
On Convergence of Incremental Gradient for Non-convex Smooth Functions ICML 2024
Stabilized Proximal-Point Methods for Federated Optimization NIPS 2024
Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates ICLR 2024
The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication COLT 2024
Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction NIPS 2023
Special Properties of Gradient Descent with Large Learning Rates ICML 2023
Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees ICML 2023
Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning NIPS 2022
Decentralized Local Stochastic Extra-Gradient for Variational Inequalities NIPS 2022
Taming GANs with Lookahead-Minmax ICLR 2021
An Improved Analysis of Gradient Tracking for Decentralized Machine Learning NIPS 2021
RelaySum for Decentralized Deep Learning on Heterogeneous Data NIPS 2021
Breaking the centralized barrier for cross-device federated learning NIPS 2021
Decentralized Deep Learning with Arbitrary Communication Compression ICLR 2020
Ensemble Distillation for Robust Model Fusion in Federated Learning NIPS 2020
Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization NIPS 2018
Sparsified SGD with Memory NIPS 2018
Safe Adaptive Importance Sampling NIPS 2017