conftrace_

Sebastian Stich

17 papers · 2018–2024 · 3 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+10 more ↓ 🌍 Conference Polyglot (3) 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🏃 Academic Marathon (6)
🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (10) 🌍 Conference Polyglot (3) 🤝 Dynamic Duo (12) 🔬 Deep Specialist (10) 💎 Century Club (17) Prolific Year (5) 🗃️ Keyword Collector (68) The Questioner 🔥 Unstoppable (5)

Conferences

ICML (11) AISTATS (5) NIPS (1)

Papers

Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction NIPS 2024 ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training ICML 2022 Masked Training of Neural Networks with Partial Gradients AISTATS 2022 ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally! ICML 2022 A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free! AISTATS 2021 Consensus Control for Decentralized Deep Learning ICML 2021 Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data ICML 2021 LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads AISTATS 2021 Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates AISTATS 2021 SCAFFOLD: Stochastic Controlled Averaging for Federated Learning ICML 2020 A Unified Theory of Decentralized SGD with Changing Topology and Local Updates ICML 2020 Extrapolation for Large-batch Training in Deep Learning ICML 2020 Is Local SGD Better than Minibatch SGD? ICML 2020 Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication ICML 2019 Error Feedback Fixes SignSGD and other Gradient Compression Schemes ICML 2019 Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems AISTATS 2018 On Matching Pursuit and Coordinate Descent ICML 2018