Francesco Orabona
Artificial Intelligence · 2008–2019
A researcher in the Science corpus: 11 papers; trusts 808 researchers and is trusted by 254 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 141 citations into it; #3,417 of 36,961 by trust here, #5,673 by citations
- Optimization & Training — 69 citations into it; #530 of 2,605 by trust here, #975 by citations
- Computer Vision and Pattern Recognition — 67 citations into it; #3,209 of 21,973 by trust here, #8,000 by citations
- Management Science and Operations Research — 46 citations into it; #947 of 12,201 by trust here, #2,211 by citations
- Computational Mechanics — 35 citations into it; #641 of 10,021 by trust here, #2,042 by citations
- Representation & Self-Supervised Learning — 27 citations into it; #1,400 of 3,156 by trust here, #1,507 by citations
- Statistical Learning Theory — 23 citations into it
- Numerical Analysis — 16 citations into it
Whom Francesco Orabona trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yurii E. Nesterov
- Nicolò Cesa-Bianchi
- Alex Krizhevsky
- Tong Zhang
- John C. Duchi
- Yann LeCun
- Elad Hazan
- Diederik P. Kingma
- Peter Auer
- Geoffrey E. Hinton
Who trusts Francesco Orabona overall
- Ashok Cutkosky
- Warrren B Powell
- Ilja Kuzborskij
- Ian Waudby-Smith
- Yu-Xiong Wang
- Han-Jia Ye
- Tianbao Yang
- Sharan Vaswani
- Ryan D'Orazio
- Zi-Yan Liu
Papers from Francesco Orabona's perspective
Ordered by how strongly the researchers Francesco Orabona 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
- Safety in numbers: Learning categories from few examples with multi model knowledge transfer (2010) — 231 citations
- Learning Categories From Few Examples With Multi Model Knowledge Transfer (2014) — 174 citations
- From N to N+1: Multiclass Transfer Incremental Learning (2013) — 151 citations
- On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes (2018) — 345 citations
- Momentum-Based Variance Reduction in Non-Convex SGD (2019) — 553 citations
- The projectron: a bounded kernel-based Perceptron (2008) — 127 citations
- A Modern Introduction to Online Learning (2019) — 559 citations
- Improved Strongly Adaptive Online Learning using Coin Betting (2016) — 95 citations
- Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning (2014) — 106 citations
- Training Deep Networks without Learning Rates Through Coin Betting (2017) — 126 citations
- Stability and Hypothesis Transfer Learning (2013) — 195 citations