Michael Kearns
Artificial Intelligence · 1987–2019
A researcher in the Science corpus: 46 papers; trusts 164 researchers and is trusted by 3,444 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 323 citations into it; #392 of 36,961 by trust here, #860 by citations
- Safety Research — 102 citations into it; #358 of 5,835 by trust here, #158 by citations
- AI Ethics, Fairness & Society — 90 citations into it; #251 of 496 by trust here, #48 by citations
- Safety, Robustness & Interpretability — 81 citations into it; #136 of 2,259 by trust here, #140 by citations
- Management Science and Operations Research — 71 citations into it; #228 of 12,201 by trust here, #127 by citations
- Sociology and Political Science — 69 citations into it; #2,688 of 22,891 by trust here, #837 by citations
- Statistics and Probability — 58 citations into it
- Reinforcement Learning — 52 citations into it; #67 of 2,250 by trust here, #127 by citations
Whom Michael Kearns trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Leslie G. Valiant
- David Haussler
- Richard S. Sutton
- Robert E. Schapire
- Cynthia Dwork
- Vladimir Naumovich Vapnik
- Yoav Freund
- Luc Devroye
- Matthew Joseph
- Andrew Barto
Who trusts Michael Kearns overall
- Lihong Li
- Vitaly Feldman
- Michael L. Littman
- Nan Jiang
- Sergey Levine
- Ian Osband
- Pieter Abbeel
- Avrim Blum
- Thomas G. Dietterich
- Alekh Agarwal
Papers from Michael Kearns's perspective
Ordered by how strongly the researchers Michael Kearns 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)
- Gradient-based learning applied to document recognition
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Learning Multiple Layers of Features from Tiny Images
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Near-Optimal Reinforcement Learning in Polynomial Time (2002) — 1,236 citations
- Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System (2011) — 428 citations
- A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes (1999)
- Efficient noise-tolerant learning from statistical queries (1998)
- Efficient Reinforcement Learning in Factored MDPs (1999)
- Fairness in Learning: Classic and Contextual Bandits (2016) — 514 citations
- An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering (1997)
- Learning from Multiple Sources (2006) — 375 citations
- A general lower bound on the number of examples needed for learning (1988)
- Learning in the presence of malicious errors (1988)
- Toward efficient agnostic learning (2004) — 452 citations
- Fairness in Reinforcement Learning (2016) — 234 citations
- Reinforcement learning for optimized trade execution (2006) — 313 citations
- An Empirical Study of Rich Subgroup Fairness for Machine Learning (2018) — 228 citations
- Graphical Models for Game Theory (2001) — 711 citations
- Differentially Private Fair Learning (2018) — 174 citations
- Meritocratic Fairness for Cross-Population Selection (2017) — 56 citations
- Online Learning with an Unknown Fairness Metric (2018) — 152 citations
- Rawlsian Fairness for Machine Learning (2016) — 88 citations
- Meritocratic Fairness for Infinite and Contextual Bandits (2018) — 49 citations