Sebastian U Stich
29 papers · 2017–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (24) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Keyword Champion
(2)
π
Triple Crown
π¬
Deep Specialist
(22)
π€
Dynamic Duo
(11)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(112)
Top co-authors
Research topics
Machine Learning
(29)
Optimization & Theory Β· Machine Learning
(28)
Mathematics & Optimization
(12)
Optimization
(12)
Artificial Intelligence
(6)
Deep Learning
(6)
Learning Paradigms Β· Artificial Intelligence
(6)
Learning Paradigms Β· Machine Learning
(4)
Optimization & Theory Β· Deep Learning
(4)
Computer Science
(2)
Systems
(2)
Techniques
(2)
Application Areas
(1)
Bayesian & Probabilistic
(1)
Mathematics
(1)
Keywords
federated learning
(9)
distributed learning
(8)
stochastic optimization
(6)
convergence rate
(6)
stochastic gradient descent
(6)
distributed optimization
(5)
decentralized optimization
(4)
communication complexity
(4)
convergence guarantee
(4)
communication compression
(4)
non-convex optimization
(3)
communication efficiency
(3)
variance reduction
(3)
error compensation
(2)
decentralized learning
(2)
variational inequality
(2)
gradient clipping
(2)
distributed training
(2)
convex optimization
(2)
client drift
(2)
Papers
Decoupled SGDA for Games with Intermittent Strategy Communication
ICML 2025
Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization
ICML 2025
Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods
ICLR 2025
Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis
AISTATS 2025
Scalable Decentralized Learning with Teleportation
ICLR 2025
Towards Faster Decentralized Stochastic Optimization with Communication Compression
ICLR 2025
An improved analysis of per-sample and per-update clipping in federated learning
ICLR 2024
Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates
ICLR 2024
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
On Convergence of Incremental Gradient for Non-convex Smooth Functions
ICML 2024
Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions
ICML 2024
Stabilized Proximal-Point Methods for Federated Optimization
NeurIPS 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
NeurIPS 2023
Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees
ICML 2023
Special Properties of Gradient Descent with Large Learning Rates
ICML 2023
Decentralized Local Stochastic Extra-Gradient for Variational Inequalities
NeurIPS 2022
Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning
NeurIPS 2022
An Improved Analysis of Gradient Tracking for Decentralized Machine Learning
NeurIPS 2021
Breaking the centralized barrier for cross-device federated learning
NeurIPS 2021
RelaySum for Decentralized Deep Learning on Heterogeneous Data
NeurIPS 2021
Taming GANs with Lookahead-Minmax
ICLR 2021
Decentralized Deep Learning with Arbitrary Communication Compression
ICLR 2020
Ensemble Distillation for Robust Model Fusion in Federated Learning
NeurIPS 2020
Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization
NeurIPS 2018
Sparsified SGD with Memory
NeurIPS 2018
Safe Adaptive Importance Sampling
NeurIPS 2017