Rong Ge
Artificial Intelligence · 2010–2019
A researcher in the Science corpus: 28 papers; trusts 769 researchers and is trusted by 775 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 324 citations into it; #1,188 of 36,961 by trust here, #1,201 by citations
- Optimization & Training — 134 citations into it; #418 of 2,605 by trust here, #362 by citations
- Computational Mechanics — 131 citations into it; #202 of 10,021 by trust here, #154 by citations
- Computer Vision and Pattern Recognition — 117 citations into it; #5,753 of 21,973 by trust here, #3,410 by citations
- Statistics and Probability — 92 citations into it; #12,297 of 13,188 by trust here, #6,500 by citations
- Computational Theory and Mathematics — 76 citations into it; #1,029 of 12,489 by trust here, #650 by citations
- Signal Processing — 69 citations into it; #765 of 7,592 by trust here, #651 by citations
- Statistical Learning Theory — 52 citations into it; #340 of 1,040 by trust here, #319 by citations
Whom Rong Ge trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yurii E. Nesterov
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Francis R. Bach
- Kaiming He
- Diederik P. Kingma
- Yann LeCun
- Sham M. Kakade
- E.J. Candes
Who trusts Rong Ge overall
- Yuanzhi Li
- Zeyuan Allen-Zhu
- Simon Shaolei Du
- Jason D. Lee
- Sanjeev Arora
- Chi Jin
- Tengyu Ma
- Samet Oymak
- Prateek Jain
- Anima Anandkumar
Papers from Rong Ge's perspective
Ordered by how strongly the researchers Rong Ge 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
- Generalization and Equilibrium in Generative Adversarial Nets (GANs) (2017) — 727 citations
- Stronger generalization bounds for deep nets via a compression approach (2018) — 714 citations
- Escaping From Saddle Points - Online Stochastic Gradient for Tensor Decomposition (2015) — 1,144 citations
- Provable Bounds for Learning Some Deep Representations (2013) — 342 citations
- Tensor decompositions for learning latent variable models (2012) — 1,214 citations
- How to Escape Saddle Points Efficiently (2017) — 945 citations
- Matrix Completion has No Spurious Local Minimum (2016) — 633 citations
- Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization (2015) — 157 citations
- Efficient approaches for escaping higher order saddle points in non-convex optimization (2016) — 142 citations
- Learning Topic Models -- Going beyond SVD (2012) — 459 citations
- No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis (2017) — 478 citations
- A Practical Algorithm for Topic Modeling with Provable Guarantees (2012) — 462 citations
- Learning One-hidden-layer Neural Networks with Landscape Design (2017) — 267 citations
- Simple, Efficient, and Neural Algorithms for Sparse Coding (2015) — 200 citations
- Rethinking learning rate schedules for stochastic optimization (2018) — 14 citations
- On the Ability of Neural Nets to Express Distributions (2017) — 89 citations
- High-Dimensional Robust Mean Estimation in Nearly-Linear Time (2018) — 132 citations
- Provable learning of noisy-OR networks (2016) — 27 citations
- The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure (2019) — 188 citations
- New Algorithms for Learning in Presence of Errors (2011) — 313 citations