Zeyuan Allen-Zhu
Artificial Intelligence · 2014–2021
A researcher in the Science corpus: 23 papers; trusts 1,501 researchers and is trusted by 1,198 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 738 citations into it; #850 of 36,961 by trust here, #980 by citations
- Optimization & Training — 341 citations into it; #109 of 2,605 by trust here, #194 by citations
- Computer Vision and Pattern Recognition — 236 citations into it; #4,302 of 21,973 by trust here, #6,987 by citations
- Computational Mechanics — 202 citations into it; #111 of 10,021 by trust here, #516 by citations
- Statistical Learning Theory — 143 citations into it; #552 of 1,040 by trust here, #571 by citations
- Scaling & Learning Theory — 110 citations into it; #40 of 429 by trust here, #62 by citations
- Model Architectures — 96 citations into it; #1,064 of 2,288 by trust here, #1,670 by citations
- Computational Theory and Mathematics — 88 citations into it; #4,027 of 12,489 by trust here, #4,101 by citations
Whom Zeyuan Allen-Zhu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Tong Zhang
- Shai Shalev-Shwartz
- Yurii E. Nesterov
- Elad Hazan
- Yuanzhi Li
- Julien Mairal
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Sanjeev Arora
Who trusts Zeyuan Allen-Zhu overall
- Yuanzhi Li
- Damek Davis
- Peter Richtárik
- Difan Zou
- Jakub Konecný
- Simon Shaolei Du
- Quanquan Gu
- Yair Carmon
- Jason D. Lee
- Greg Yang
Papers from Zeyuan Allen-Zhu's perspective
Ordered by how strongly the researchers Zeyuan Allen-Zhu 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
- 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
- Variance Reduction for Faster Non-Convex Optimization (2016) — 414 citations
- Katyusha: the first direct acceleration of stochastic gradient methods (2016) — 624 citations
- Neon2: Finding Local Minima via First-Order Oracles (2017) — 145 citations
- Natasha 2: Faster Non-Convex Optimization Than SGD (2017) — 259 citations
- Is Q-learning Provably Efficient? (2018) — 921 citations
- How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD (2018) — 186 citations
- Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent (2014) — 309 citations
- What Can ResNet Learn Efficiently, Going Beyond Kernels? (2019) — 200 citations
- On the Convergence Rate of Training Recurrent Neural Networks (2018) — 205 citations
- Optimal Black-Box Reductions Between Optimization Objectives (2016) — 98 citations
- Can SGD Learn Recurrent Neural Networks with Provable Generalization? (2019) — 61 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
- Byzantine Stochastic Gradient Descent (2018) — 324 citations
- Backward Feature Correction: How Deep Learning Performs Deep Learning (2020) — 125 citations
- Much Faster Algorithms for Matrix Scaling (2017) — 123 citations
- Exploiting the Structure: Stochastic Gradient Methods Using Raw Clusters (2016) — 29 citations