Nicolò Cesa-Bianchi
Artificial Intelligence · with Gentile · 1993–2017
A researcher in the Science corpus: 22 papers; trusts 171 researchers and is trusted by 3,439 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 210 citations into it; #382 of 36,961 by trust here, #697 by citations
- Management Science and Operations Research — 164 citations into it; #36 of 12,201 by trust here, #45 by citations
- Statistical Learning Theory — 75 citations into it; #367 of 1,040 by trust here, #393 by citations
- Reinforcement Learning — 61 citations into it; #73 of 2,250 by trust here, #107 by citations
- Statistics and Probability — 55 citations into it
- Computer Networks and Communications — 40 citations into it; #228 of 9,996 by trust here, #302 by citations
- Optimization & Training — 39 citations into it; #1,152 of 2,605 by trust here, #1,156 by citations
- Theoretical Computer Science — 37 citations into it; #106 of 457 by trust here, #53 by citations
Whom Nicolò Cesa-Bianchi trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Peter Auer
- Vladimir Naumovich Vapnik
- Yoav Freund
- Nick Littlestone
- Jorma Rissanen
- Manfred K. Warmuth
- Robert E. Schapire
- Sébastien Bubeck
- Richard S. Sutton
- W. Hoeffding
Who trusts Nicolò Cesa-Bianchi overall
- Alekh Agarwal
- Elad Hazan
- Tor Lattimore
- Steven C. H. Hoi
- Francesco Orabona
- R´emi Munos
- Sébastien Bubeck
- Csaba Szepesvari
- Ohad Shamir
- Sham M. Kakade
Papers from Nicolò Cesa-Bianchi's perspective
Ordered by how strongly the researchers Nicolò Cesa-Bianchi 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)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Finite-time Analysis of the Multiarmed Bandit Problem (2002) — 7,574 citations
- Prediction, learning, and games (2006) — 4,451 citations
- The Nonstochastic Multiarmed Bandit Problem (2002) — 2,743 citations
- Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems (2012) — 1,783 citations
- On the generalization ability of on-line learning algorithms (2001) — 624 citations
- Gambling in a rigged casino: The adversarial multi-armed bandit problem (1995)
- Improved second-order bounds for prediction with expert advice (2005) — 288 citations
- PAC-Bayesian Inequalities for Martingales (2011) — 137 citations
- Combinatorial Bandits (2012) — 505 citations
- Adaptive and Self-Confident On-Line Learning Algorithms (2000) — 279 citations
- Online Learning with Switching Costs and Other Adaptive Adversaries (2013) — 133 citations
- IEEE TRANSACTIONS ON INFORMATION THEORY , VOL . ? , NO . ? , ? 200 ? 1 Improved Risk Tail Bounds for On-Line Algorithms (2007) — 72 citations
- Mirror Descent Meets Fixed Share (and feels no regret) (2012) — 106 citations
- Bandits With Heavy Tail (2012) — 338 citations
- Towards Minimax Policies for Online Linear Optimization with Bandit Feedback (2012) — 175 citations
- Boltzmann Exploration Done Right (2017) — 205 citations
- Linear Algorithms for Online Multitask Classification (2010) — 201 citations
- PAC-Bayes-Bernstein Inequality for Martingales and its Application to Multiarmed Bandits (2011) — 29 citations
- A Gang of Bandits (2013) — 174 citations
- A new look at shifting regret (2012) — 32 citations