Dimitris Papailiopoulos
Artificial Intelligence · 2012–2023
A researcher in the Science corpus: 27 papers; trusts 1,035 researchers and is trusted by 67 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 653 citations into it; #4,249 of 36,961 by trust here, #3,088 by citations
- Optimization & Training — 288 citations into it; #1,077 of 2,605 by trust here, #521 by citations
- Computer Vision and Pattern Recognition — 235 citations into it
- Computer Networks and Communications — 170 citations into it; #1,553 of 9,996 by trust here, #1,345 by citations
- Computational Mechanics — 120 citations into it; #5,194 of 10,021 by trust here, #1,995 by citations
- Information Systems — 81 citations into it
- Safety, Robustness & Interpretability — 77 citations into it
- Hardware and Architecture — 70 citations into it
Whom Dimitris Papailiopoulos trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Yann LeCun
- Karen Simonyan
- Yoshua Bengio
- L. Eon Bottou
- Ilya Sutskever
- Diederik P. Kingma
- Yurii E. Nesterov
Who trusts Dimitris Papailiopoulos overall
- Deepesh Data
- Zachary B. Charles
- Sebastian U. Stich
- Suhas N. Diggavi
- Tian Li
- Ankit Singh Rawat
- Linqi Song
- Hongyi Wang
- Lingjiao Chen
- Sanghamitra Dutta
Papers from Dimitris Papailiopoulos's perspective
Ordered by how strongly the researchers Dimitris Papailiopoulos trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- 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)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Perturbed Iterate Analysis for Asynchronous Stochastic Optimization (2015) — 252 citations
- Federated Learning with Matched Averaging (2020) — 1,404 citations
- Attack of the Tails: Yes, You Really Can Backdoor Federated Learning (2020) — 829 citations
- The Effect of Network Width on the Performance of Large-batch Training (2018) — 24 citations
- Cyclades: Conflict-free Asynchronous Machine Learning (2016) — 63 citations
- Looped Transformers as Programmable Computers (2023) — 222 citations
- DRACO: Byzantine-resilient Distributed Training via Redundant Gradients (2018) — 274 citations
- ATOMO: Communication-efficient Learning via Atomic Sparsification (2018) — 392 citations
- Does Data Augmentation Lead to Positive Margin? (2019) — 38 citations
- Gradient Diversity Empowers Distributed Learning (2017) — 12 citations
- Gradient Coding Using the Stochastic Block Model (2018) — 26 citations
- LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks (2022) — 200 citations
- Permutation-Based SGD: Is Random Optimal? (2021) — 16 citations
- Closing the convergence gap of SGD without replacement (2020) — 75 citations
- Bad Global Minima Exist and SGD Can Reach Them (2019) — 89 citations
- SysML: The New Frontier of Machine Learning Systems (2019) — 23 citations
- MLSys: The New Frontier of Machine Learning Systems (2019) — 25 citations
- DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation (2019) — 149 citations
- A Geometric Perspective on the Transferability of Adversarial Directions (2018) — 17 citations
- Draco: Robust Distributed Training against Adversaries (2018)