Yuanzhi Li
Artificial Intelligence · with Allen-Zhu · 2015–2021
A researcher in the Science corpus: 29 papers; trusts 1,862 researchers and is trusted by 832 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 871 citations into it; #1,111 of 36,961 by trust here, #921 by citations
- Computer Vision and Pattern Recognition — 323 citations into it; #3,376 of 21,973 by trust here, #2,631 by citations
- Optimization & Training — 298 citations into it; #272 of 2,605 by trust here, #261 by citations
- Statistical Learning Theory — 196 citations into it; #304 of 1,040 by trust here, #226 by citations
- Scaling & Learning Theory — 171 citations into it; #9 of 429 by trust here, #37 by citations
- Computational Mechanics — 137 citations into it; #1,893 of 10,021 by trust here, #2,790 by citations
- Model Architectures — 119 citations into it; #328 of 2,288 by trust here, #647 by citations
- Natural Language Processing — 107 citations into it; #2,842 of 5,725 by trust here, #3,133 by citations
Whom Yuanzhi Li trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Sanjeev Arora
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Kaiming He
- Diederik P. Kingma
- Zeyuan Allen-Zhu
- Ilya Sutskever
- Yann LeCun
- Rong Ge
Who trusts Yuanzhi Li overall
- Zeyuan Allen-Zhu
- Simon Shaolei Du
- Difan Zou
- Sanjeev Arora
- Jason D. Lee
- Colin Wei
- Tengyu Ma
- Quanquan Gu
- M. Soltanolkotabi
- Gilad Yehudai
Papers from Yuanzhi Li's perspective
Ordered by how strongly the researchers Yuanzhi Li 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
- LoRA: Low-Rank Adaptation of Large Language Models (2021) — 21,145 citations
- A Convergence Theory for Deep Learning via Over-Parameterization (2018) — 1,651 citations
- Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers (2018) — 841 citations
- Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data (2018) — 687 citations
- Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees (2018) — 249 citations
- An Alternative View: When Does SGD Escape Local Minima? (2018) — 349 citations
- Convergence Analysis of Two-layer Neural Networks with ReLU Activation (2017) — 685 citations
- Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks (2019) — 341 citations
- Neon2: Finding Local Minima via First-Order Oracles (2017) — 145 citations
- Algorithmic Framework for Model-based Reinforcement Learning with Theoretical Guarantees (2018) — 17 citations
- What Can ResNet Learn Efficiently, Going Beyond Kernels? (2019) — 200 citations
- On the Convergence Rate of Training Recurrent Neural Networks (2018) — 205 citations
- Linear Algebraic Structure of Word Senses, with Applications to Polysemy (2016) — 346 citations
- Algorithmic Regularization in Over-parameterized Matrix Recovery (2017) — 31 citations
- Can SGD Learn Recurrent Neural Networks with Provable Generalization? (2019) — 61 citations
- A Latent Variable Model Approach to PMI-based Word Embeddings (2015) — 400 citations
- Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning (2020) — 476 citations
- Feature Purification: How Adversarial Training Performs Robust Deep Learning (2020) — 177 citations
- Backward Feature Correction: How Deep Learning Performs Deep Learning (2020) — 125 citations
- Much Faster Algorithms for Matrix Scaling (2017) — 123 citations