Sebastian U. Stich
Artificial Intelligence · 2011–2022
A researcher in the Science corpus: 25 papers; trusts 1,692 researchers and is trusted by 339 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,404 citations into it; #1,430 of 36,961 by trust here, #1,093 by citations
- Optimization & Training — 713 citations into it; #92 of 2,605 by trust here, #185 by citations
- Computer Vision and Pattern Recognition — 316 citations into it; #4,826 of 21,973 by trust here, #4,538 by citations
- Federated & Distributed Learning — 299 citations into it; #2 of 319 by trust here, #11 by citations
- Computational Mechanics — 280 citations into it; #568 of 10,021 by trust here, #883 by citations
- Computer Networks and Communications — 241 citations into it; #451 of 9,996 by trust here, #616 by citations
- Efficiency & Compression — 155 citations into it; #54 of 1,273 by trust here, #184 by citations
- Management Science and Operations Research — 137 citations into it; #10,057 of 12,201 by trust here, #5,753 by citations
Whom Sebastian U. Stich trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Ohad Shamir
- L. Eon Bottou
- Kaiming He
- Francis R. Bach
- Yurii E. Nesterov
- Geoffrey E. Hinton
- Tong Zhang
- Yann LeCun
- Yoshua Bengio
Who trusts Sebastian U. Stich overall
- Jianyu Wang
- Ahmed Khaled
- Sai Praneeth Karimireddy
- Anastasia Koloskova
- Farzin Haddadpour
- Cong Xie
- Peter Richtárik
- Martin Jaggi
- Hao Yu
- Tao Lin
Papers from Sebastian U. Stich's perspective
Ordered by how strongly the researchers Sebastian U. Stich trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Advances and Open Problems in Federated Learning (2019) — 9,019 citations
- SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning (2019) — 406 citations
- Error Feedback Fixes SignSGD and other Gradient Compression Schemes (2019) — 655 citations
- Don't Use Large Mini-Batches, Use Local SGD (2018) — 470 citations
- Local SGD Converges Fast and Communicates Little (2018) — 1,280 citations
- Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication (2019) — 612 citations
- SCAFFOLD: Stochastic Controlled Averaging for Federated Learning (2019) — 4,191 citations
- The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication (2019) — 184 citations
- Dynamic Model Pruning with Feedback (2020) — 232 citations
- Decentralized Deep Learning with Arbitrary Communication Compression (2019) — 272 citations
- A Field Guide to Federated Optimization (2021) — 487 citations
- Sparsified SGD with Memory (2018) — 894 citations
- Is Local SGD Better than Minibatch SGD? (2020) — 290 citations
- Global linear convergence of Newton's method without strong-convexity or Lipschitz gradients (2018) — 63 citations
- A Unified Theory of Decentralized SGD with Changing Topology and Local Updates (2020) — 652 citations
- Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization (2018) — 49 citations
- Unified Optimal Analysis of the (Stochastic) Gradient Method (2019) — 138 citations
- Optimization of Convex Functions with Random Pursuit (2011) — 58 citations
- Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning (2020) — 251 citations
- Safe Adaptive Importance Sampling (2017) — 60 citations