Yair Carmon
Artificial Intelligence · 2016–2024
A researcher in the Science corpus: 11 papers; trusts 679 researchers and is trusted by 145 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 386 citations into it; #2,824 of 36,961 by trust here, #3,500 by citations
- Computer Vision and Pattern Recognition — 244 citations into it; #4,423 of 21,973 by trust here, #3,189 by citations
- Optimization & Training — 130 citations into it; #540 of 2,605 by trust here, #666 by citations
- Computational Mechanics — 76 citations into it; #1,345 of 10,021 by trust here, #1,312 by citations
- Evaluation & Benchmarks — 75 citations into it
- Safety, Robustness & Interpretability — 65 citations into it; #1,134 of 2,259 by trust here, #832 by citations
- Representation & Self-Supervised Learning — 64 citations into it
- Computational Theory and Mathematics — 56 citations into it; #4,801 of 12,489 by trust here, #4,888 by citations
Whom Yair Carmon trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yurii E. Nesterov
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yann LeCun
- Shai Shalev-Shwartz
- Zeyuan Allen-Zhu
- Yoshua Bengio
- Diederik P. Kingma
- Tong Zhang
- Kaiming He
Who trusts Yair Carmon overall
- Zeyuan Allen-Zhu
- Rachel A. Ward
- Chi Jin
- Cong Fang
- Simon Shaolei Du
- Yuanzhi Li
- Leonard Adolphs
- Jonas Köhler
- Tengyu Ma
- Sven Gowal
Papers from Yair Carmon's perspective
Ordered by how strongly the researchers Yair Carmon 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
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- 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
- Unlabeled Data Improves Adversarial Robustness (2019) — 814 citations
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time (2022) — 1,632 citations
- No bad local minima: Data independent training error guarantees for multilayer neural networks (2016) — 244 citations
- DataComp: In search of the next generation of multimodal datasets (2023) — 734 citations
- Accelerated Methods for Non-Convex Optimization (2016) — 196 citations
- "Convex Until Proven Guilty": Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions (2017) — 165 citations
- Lower bounds for finding stationary points I (2017) — 348 citations
- Lower bounds for non-convex stochastic optimization (2019) — 476 citations
- Variance Reduction for Matrix Games (2019) — 81 citations
- DataComp-LM: In search of the next generation of training sets for language models (2024) — 374 citations
- Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization (2021) — 331 citations