Sanjeev Arora
Artificial Intelligence · Symposium on the Theory of Computing · 1992–2024
A researcher in the Science corpus: 49 papers; trusts 2,151 researchers and is trusted by 2,229 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 801 citations into it; #704 of 36,961 by trust here, #805 by citations
- Computer Vision and Pattern Recognition — 303 citations into it; #1,723 of 21,973 by trust here, #1,212 by citations
- Optimization & Training — 227 citations into it; #549 of 2,605 by trust here, #513 by citations
- Natural Language Processing — 155 citations into it; #802 of 5,725 by trust here, #1,068 by citations
- Representation & Self-Supervised Learning — 153 citations into it; #426 of 3,156 by trust here, #467 by citations
- Computational Mechanics — 124 citations into it; #995 of 10,021 by trust here, #775 by citations
- Scaling & Learning Theory — 115 citations into it; #31 of 429 by trust here, #34 by citations
- Computational Theory and Mathematics — 101 citations into it; #329 of 12,489 by trust here, #507 by citations
Whom Sanjeev Arora trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Alex Krizhevsky
- Yoshua Bengio
- Kaiming He
- Yann LeCun
- Ilya Sutskever
- Tomas Mikolov
- Karen Simonyan
- Jimmy Ba
Who trusts Sanjeev Arora overall
- Yuanzhi Li
- Zeyuan Allen-Zhu
- Simon Shaolei Du
- Srinath T. V. Setty
- Eli Ben-Sasson
- Colin Wei
- Subhash Khot
- Tengyu Ma
- Wei Hu
- Yoshua Bengio
Papers from Sanjeev Arora's perspective
Ordered by how strongly the researchers Sanjeev Arora 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
- A Simple but Tough-to-Beat Baseline for Sentence Embeddings (2017) — 1,419 citations
- Generalization and Equilibrium in Generative Adversarial Nets (GANs) (2017) — 727 citations
- On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization (2018) — 563 citations
- Stronger generalization bounds for deep nets via a compression approach (2018) — 714 citations
- Provable Bounds for Learning Some Deep Representations (2013) — 342 citations
- Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks (2019) — 1,081 citations
- A Theoretical Analysis of Contrastive Unsupervised Representation Learning (2019) — 910 citations
- Do GANs actually learn the distribution? An empirical study (2017) — 199 citations
- On Exact Computation with an Infinitely Wide Neural Net (2019) — 1,059 citations
- Implicit Regularization in Deep Matrix Factorization (2019) — 634 citations
- An Exponential Learning Rate Schedule for Deep Learning (2019) — 272 citations
- Do GANs learn the distribution? Some Theory and Empirics (2018) — 171 citations
- The Multiplicative Weights Update Method: a Meta-Algorithm and Applications (2012) — 1,187 citations
- Theoretical Analysis of Auto Rate-Tuning by Batch Normalization (2018) — 146 citations
- Learning Topic Models -- Going beyond SVD (2012) — 459 citations
- Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks (2019) — 171 citations
- A Practical Algorithm for Topic Modeling with Provable Guarantees (2012) — 462 citations
- Why are deep nets reversible: A simple theory, with implications for training (2015) — 55 citations
- A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks (2018) — 350 citations
- Expander flows, geometric embeddings and graph partitioning (2004) — 674 citations