Yingyu Liang
Artificial Intelligence · 2014–2020
A researcher in the Science corpus: 21 papers; trusts 1,280 researchers and is trusted by 765 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 383 citations into it; #1,190 of 36,961 by trust here, #1,635 by citations
- Computer Vision and Pattern Recognition — 166 citations into it; #3,491 of 21,973 by trust here, #2,869 by citations
- Representation & Self-Supervised Learning — 104 citations into it; #459 of 3,156 by trust here, #714 by citations
- Optimization & Training — 100 citations into it; #1,208 of 2,605 by trust here, #1,180 by citations
- Natural Language Processing — 96 citations into it; #829 of 5,725 by trust here, #1,271 by citations
- Computational Mechanics — 69 citations into it; #4,579 of 10,021 by trust here, #2,583 by citations
- Statistical Learning Theory — 61 citations into it; #428 of 1,040 by trust here, #279 by citations
- Scaling & Learning Theory — 45 citations into it; #27 of 429 by trust here, #82 by citations
Whom Yingyu Liang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Yann LeCun
- Ilya Sutskever
- Kaiming He
- Tomas Mikolov
- Sanjeev Arora
- Ruslan Salakhutdinov
Who trusts Yingyu Liang overall
- Yuanzhi Li
- Zeyuan Allen-Zhu
- Sanjeev Arora
- Simon Shaolei Du
- Kawin Ethayarajh
- Tengyu Ma
- Difan Zou
- Colin Wei
- John Wieting
- Alberto Bietti
Papers from Yingyu Liang's perspective
Ordered by how strongly the researchers Yingyu Liang trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- 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
- Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers (2018) — 841 citations
- Scalable Kernel Methods via Doubly Stochastic Gradients (2014) — 238 citations
- Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data (2018) — 687 citations
- Diverse Neural Network Learns True Target Functions (2016) — 147 citations
- Why are deep nets reversible: A simple theory, with implications for training (2015) — 55 citations
- Linear Algebraic Structure of Word Senses, with Applications to Polysemy (2016) — 346 citations
- A Latent Variable Model Approach to PMI-based Word Embeddings (2015) — 400 citations
- Diversity Leads to Generalization in Neural Networks (2016) — 36 citations
- Scale Up Nonlinear Component Analysis with Doubly Stochastic Gradients (2015) — 45 citations
- A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors (2018) — 109 citations
- Gradients as Features for Deep Representation Learning (2020) — 46 citations
- Improved Distributed Principal Component Analysis (2014) — 158 citations
- Recovery guarantee of weighted low-rank approximation via alternating minimization (2016) — 52 citations
- Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis (2019) — 434 citations
- Differentially Private Clustering in High-Dimensional Euclidean Spaces (2017) — 92 citations
- Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations (2017) — 18 citations
- Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates (2016) — 30 citations
- RAND-WALK: A Latent Variable Model Approach to Word Embeddings (2015) — 67 citations