Tengyu Ma
Artificial Intelligence · 2002–2024
A researcher in the Science corpus: 57 papers; trusts 3,151 researchers and is trusted by 2,118 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,522 citations into it; #651 of 36,961 by trust here, #551 by citations
- Computer Vision and Pattern Recognition — 584 citations into it; #2,096 of 21,973 by trust here, #1,592 by citations
- Optimization & Training — 382 citations into it; #354 of 2,605 by trust here, #285 by citations
- Reinforcement Learning — 222 citations into it; #1,284 of 2,250 by trust here, #888 by citations
- Natural Language Processing — 216 citations into it; #827 of 5,725 by trust here, #1,271 by citations
- Representation & Self-Supervised Learning — 208 citations into it; #267 of 3,156 by trust here, #389 by citations
- Computational Mechanics — 202 citations into it; #697 of 10,021 by trust here, #596 by citations
- Scaling & Learning Theory — 191 citations into it; #104 of 429 by trust here, #107 by citations
Whom Tengyu Ma trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yoshua Bengio
- Kaiming He
- Ilya Sutskever
- Yann LeCun
- Jimmy Ba
- Alex Graves
- Karen Simonyan
Who trusts Tengyu Ma overall
- Yuanzhi Li
- Zeyuan Allen-Zhu
- Jason D. Lee
- Sanjeev Arora
- Simon Shaolei Du
- Colin Wei
- Leighton Pate Barnes
- Rong Ge
- Michael I. Jordan
- Jakub Konecný
Papers from Tengyu Ma's perspective
Ordered by how strongly the researchers Tengyu Ma 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- On the Opportunities and Risks of Foundation Models (2021) — 6,923 citations
- A Simple but Tough-to-Beat Baseline for Sentence Embeddings (2017) — 1,419 citations
- Fixup Initialization: Residual Learning Without Normalization (2019) — 406 citations
- Generalization and Equilibrium in Generative Adversarial Nets (GANs) (2017) — 727 citations
- Provable Bounds for Learning Some Deep Representations (2013) — 342 citations
- Identity Matters in Deep Learning (2016) — 421 citations
- MOPO: Model-based Offline Policy Optimization (2020) — 951 citations
- An Explanation of In-context Learning as Implicit Bayesian Inference (2021) — 1,108 citations
- Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss (2019) — 2,156 citations
- Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees (2018) — 249 citations
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution (2022) — 972 citations
- Verified Uncertainty Calibration (2019) — 468 citations
- Matrix Completion has No Spurious Local Minimum (2016) — 633 citations
- Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks (2019) — 341 citations
- Larger language models do in-context learning differently (2023) — 488 citations
- Data Selection for Language Models via Importance Resampling (2023) — 356 citations
- Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin (2019) — 95 citations
- Large Language Models as Tool Makers (2023) — 316 citations
- Distributed Stochastic Variance Reduced Gradient Methods and A Lower Bound for Communication Complexity (2015) — 53 citations
- Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel (2018) — 275 citations