Daniel J. Hsu
Artificial Intelligence · 2007–2020
A researcher in the Science corpus: 36 papers; trusts 862 researchers and is trusted by 717 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 518 citations into it; #1,245 of 36,961 by trust here, #1,534 by citations
- Statistics and Probability — 165 citations into it; #3,592 of 13,188 by trust here, #1,616 by citations
- Computer Vision and Pattern Recognition — 117 citations into it; #7,425 of 21,973 by trust here, #8,550 by citations
- Safety, Robustness & Interpretability — 117 citations into it; #2,189 of 2,259 by trust here, #1,024 by citations
- Statistical Learning Theory — 98 citations into it; #990 of 1,040 by trust here, #604 by citations
- Computational Theory and Mathematics — 79 citations into it
- Management Science and Operations Research — 66 citations into it; #1,183 of 12,201 by trust here, #691 by citations
- Signal Processing — 60 citations into it; #540 of 7,592 by trust here, #627 by citations
Whom Daniel J. Hsu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Tong Zhang
- Geoffrey E. Hinton
- Cynthia Dwork
- Frank McSherry
- Alex Krizhevsky
- Diederik P. Kingma
- Sanjoy Dasgupta
- Yoshua Bengio
- Sham M. Kakade
- Yann LeCun
Who trusts Daniel J. Hsu overall
- Anima Anandkumar
- Sham M. Kakade
- Francis R. Bach
- Rong Ge
- Stanislav Minsker
- Byron Boots
- Vitaly Feldman
- Prateek Jain
- Alekh Agarwal
- Sanjeev Arora
Papers from Daniel J. Hsu's perspective
Ordered by how strongly the researchers Daniel J. Hsu 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)
- 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
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Tensor decompositions for learning latent variable models (2012) — 1,214 citations
- Reconciling modern machine-learning practice and the classical bias–variance trade-off (2018) — 2,107 citations
- Multi-Label Prediction via Compressed Sensing (2009) — 443 citations
- Reconciling modern machine learning and the bias-variance trade-off (2018) — 136 citations
- Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits (2014) — 564 citations
- Certified Robustness to Adversarial Examples with Differential Privacy (2018) — 1,063 citations
- A Method of Moments for Mixture Models and Hidden Markov Models (2012) — 349 citations
- A Spectral Algorithm for Latent Dirichlet Allocation (2012) — 304 citations
- A spectral algorithm for learning Hidden Markov Models (2008) — 312 citations
- Stochastic Convex Optimization with Bandit Feedback (2011) — 250 citations
- Two models of double descent for weak features (2019) — 413 citations
- Contrastive Learning Using Spectral Methods (2013) — 100 citations
- Efficient Optimal Learning for Contextual Bandits (2011) — 325 citations
- Learning mixtures of spherical gaussians: moment methods and spectral decompositions (2012) — 336 citations
- Classification vs regression in overparameterized regimes: Does the loss function matter? (2020) — 172 citations
- Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate (2018) — 280 citations
- Hierarchical sampling for active learning (2008) — 526 citations
- Convergence Rates for Differentially Private Statistical Estimation (2012) — 52 citations
- Teaching a black-box learner (2019) — 55 citations
- FairTest: Discovering Unwarranted Associations in Data-Driven Applications (2015) — 191 citations