Lev Reyzin

Artificial Intelligence · 2010–2012

A researcher in the Science corpus: 5 papers; trusts 15 researchers and is trusted by 12 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 22 citations into it; #11,919 of 35,345 by trust here, #10,667 by citations
• Management Science and Operations Research — 18 citations into it; #3,995 of 11,946 by trust here, #2,185 by citations
• Reinforcement Learning — 15 citations into it; #1,113 of 2,242 by trust here, #1,139 by citations
• Statistical Learning Theory — 13 citations into it
• Optimization & Training — 7 citations into it

Whom Lev Reyzin trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Peter Auer
2. Nicolò Cesa-Bianchi
3. T. L. Lai Andherbertrobbins
4. J. Langford
5. Leslie G. Valiant
6. Vladimir Naumovich Vapnik
7. Michael Kearns
8. Mark Herbster
9. Peter L. Bartlett
10. Yoav Freund

Who trusts Lev Reyzin overall

1. Aleksandrs Slivkins
2. Alekh Agarwal
3. Lihong Li
4. Sébastien Bubeck
5. Akshay Krishnamurthy
6. Vitaly Feldman
7. Ilias Diakonikolas
8. Aniket Anand Deshmukh
9. Miroslav Dud'ik
10. Nicolò Cesa-Bianchi

Papers from Lev Reyzin's perspective

Ordered by how strongly the researchers Lev Reyzin trusts endorse each paper. Same corpus, a different order for every researcher.

1. Some aspects of the sequential design of experiments
2. Asymptotically efficient adaptive allocation rules
3. A decision-theoretic generalization of on-line learning and an application to boosting
4. The weighted majority algorithm
5. Asymptotically Efficient Adaptive Allocation Rules
6. ImageNet classification with deep convolutional neural networks
7. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
8. Prediction, learning, and games
9. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper
10. Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities

Their papers

• Contextual Bandit Algorithms with Supervised Learning Guarantees (2010) — 356 citations
• Efficient Optimal Learning for Contextual Bandits (2011) — 325 citations
• Statistical algorithms and a lower bound for detecting planted cliques (2012) — 247 citations
• Contextual Bandits with Linear Payoff Functions (2011) — 1,222 citations
• Non-Stochastic Bandit Slate Problems (2010) — 95 citations