Jason D. Lee
Artificial Intelligence · Neural Information Processing Systems · 2004–2023
A researcher in the Science corpus: 45 papers; trusts 1,752 researchers and is trusted by 789 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,008 citations into it; #1,173 of 36,961 by trust here, #1,185 by citations
- Optimization & Training — 438 citations into it; #331 of 2,605 by trust here, #252 by citations
- Computational Mechanics — 327 citations into it; #337 of 10,021 by trust here, #183 by citations
- Computer Vision and Pattern Recognition — 315 citations into it; #5,363 of 21,973 by trust here, #5,493 by citations
- Statistics and Probability — 235 citations into it; #1,006 of 13,188 by trust here, #686 by citations
- Statistical Learning Theory — 202 citations into it; #223 of 1,040 by trust here, #127 by citations
- Scaling & Learning Theory — 187 citations into it; #91 of 429 by trust here, #121 by citations
- Computational Theory and Mathematics — 144 citations into it; #2,163 of 12,489 by trust here, #1,770 by citations
Whom Jason D. Lee trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yurii E. Nesterov
- Robert Tibshirani
- Geoffrey E. Hinton
- Shai Shalev-Shwartz
- Ohad Shamir
- Yoshua Bengio
- Alex Krizhevsky
- Kaiming He
- Yann LeCun
- Francis R. Bach
Who trusts Jason D. Lee overall
- Simon Shaolei Du
- Sanjeev Arora
- Yuanzhi Li
- Wei Hu
- Colin Wei
- Michael I. Jordan
- Zeyuan Allen-Zhu
- Qiang Liu
- Robert Tibshirani
- Samet Oymak
Papers from Jason D. Lee's perspective
Ordered by how strongly the researchers Jason D. Lee 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
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Gradient Descent Finds Global Minima of Deep Neural Networks (2018) — 1,268 citations
- Implicit Bias of Gradient Descent on Linear Convolutional Networks (2018) — 483 citations
- Gradient Descent Converges to Minimizers (2016) — 218 citations
- Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks (2017) — 450 citations
- ℓ1-regularized Neural Networks are Improperly Learnable in Polynomial Time (2015) — 103 citations
- Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes (2019) — 345 citations
- Matrix Completion has No Spurious Local Minimum (2016) — 633 citations
- Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced (2018) — 284 citations
- Characterizing Implicit Bias in Terms of Optimization Geometry (2018) — 476 citations
- On the Power of Over-parametrization in Neural Networks with Quadratic Activation (2018) — 293 citations
- Distributed Stochastic Variance Reduced Gradient Methods and A Lower Bound for Communication Complexity (2015) — 53 citations
- Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima (2017) — 243 citations
- Few-Shot Learning via Learning the Representation, Provably (2020) — 298 citations
- Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel (2018) — 275 citations
- Learning Halfspaces and Neural Networks with Random Initialization (2015) — 39 citations
- Kernel and Rich Regimes in Overparametrized Models (2019) — 437 citations
- Kernel and Deep Regimes in Overparametrized Models (2019) — 33 citations
- When is a Convolutional Filter Easy To Learn? (2017) — 131 citations
- Convergence of Adversarial Training in Overparametrized Neural Networks (2019) — 119 citations
- Learning One-hidden-layer Neural Networks with Landscape Design (2017) — 267 citations