Sébastien Bubeck
Artificial Intelligence · 2009–2024
A researcher in the Science corpus: 28 papers; trusts 331 researchers and is trusted by 1,206 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 337 citations into it; #884 of 36,961 by trust here, #1,157 by citations
- Management Science and Operations Research — 122 citations into it; #152 of 12,201 by trust here, #149 by citations
- Optimization & Training — 79 citations into it; #157 of 2,605 by trust here, #448 by citations
- Reinforcement Learning — 70 citations into it; #201 of 2,250 by trust here, #362 by citations
- Computer Networks and Communications — 63 citations into it; #350 of 9,996 by trust here, #375 by citations
- Computer Vision and Pattern Recognition — 56 citations into it
- Safety, Robustness & Interpretability — 49 citations into it; #969 of 2,259 by trust here, #877 by citations
- Statistics and Probability — 49 citations into it
Whom Sébastien Bubeck trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Nicolò Cesa-Bianchi
- Yurii E. Nesterov
- Peter Auer
- Jean-Yves Audibert
- Eric R. Ziegel
- Robert D. Kleinberg
- Gábor Lugosi
- John C. Duchi
- Martin Jaggi
- Elad Hazan
Who trusts Sébastien Bubeck overall
- Tor Lattimore
- Daniel Russo
- R´emi Munos
- Dan Alistarh
- Kevin Scaman
- Chi Jin
- Ziwei Ji
- Csaba Szepesvari
- Nicolò Cesa-Bianchi
- David Lopez-Paz
Papers from Sébastien Bubeck's perspective
Ordered by how strongly the researchers Sébastien Bubeck 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
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- 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
- Sparks of Artificial General Intelligence: Early experiments with GPT-4 (2023) — 4,318 citations
- Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems (2012) — 1,783 citations
- Convex Optimization: Algorithms and Complexity (2014) — 2,173 citations
- Pure Exploration in Multi-armed Bandits Problems (2009) — 579 citations
- Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers (2019) — 640 citations
- Minimax Policies for Adversarial and Stochastic Bandits (2009) — 486 citations
- Adversarial examples from computational constraints (2018) — 239 citations
- Textbooks Are All You Need (2023) — 626 citations
- Is Q-learning Provably Efficient? (2018) — 921 citations
- Minimax Policies for Combinatorial Prediction Games (2011) — 87 citations
- lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits (2013) — 451 citations
- Sparsity, variance and curvature in multi-armed bandits (2017) — 68 citations
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone (2024) — 2,340 citations
- Bandits With Heavy Tail (2012) — 338 citations
- Towards Minimax Policies for Online Linear Optimization with Bandit Feedback (2012) — 175 citations
- Adversarial Examples from Cryptographic Pseudo-Random Generators (2018) — 33 citations
- X-Armed Bandits (2010) — 439 citations
- Optimal Algorithms for Non-Smooth Distributed Optimization in Networks (2018) — 177 citations
- Multiple Identifications in Multi-Armed Bandits (2012) — 190 citations
- Pure exploration in finitely-armed and continuous-armed bandits (2011) — 284 citations