Massimiliano Pontil
Artificial Intelligence · 2000–2020
A researcher in the Science corpus: 45 papers; trusts 940 researchers and is trusted by 2,215 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 502 citations into it; #575 of 36,961 by trust here, #757 by citations
- Computer Vision and Pattern Recognition — 167 citations into it; #7,226 of 21,973 by trust here, #6,262 by citations
- Statistical Learning Theory — 142 citations into it; #88 of 1,040 by trust here, #66 by citations
- Statistics and Probability — 142 citations into it; #896 of 13,188 by trust here, #783 by citations
- Optimization & Training — 127 citations into it; #184 of 2,605 by trust here, #254 by citations
- Representation & Self-Supervised Learning — 113 citations into it; #66 of 3,156 by trust here, #178 by citations
- Computational Mechanics — 101 citations into it; #16 of 10,021 by trust here, #29 by citations
- Computational Theory and Mathematics — 86 citations into it; #6,765 of 12,489 by trust here, #4,237 by citations
Whom Massimiliano Pontil trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Jonathan Baxter
- Andreas Maurer
- Yuhai Wu
- Francis R. Bach
- Theodoros Evgeniou
- Andreas Argyriou
- Geoffrey E. Hinton
- Yoshua Bengio
- Robert Tibshirani
- Diederik P. Kingma
Who trusts Massimiliano Pontil overall
- Yu Zhang
- Qiang Yang
- Andreas Maurer
- Lorenzo Rosasco
- Mohammad Rostami
- Carlo Ciliberto
- Anastasia Pentina
- Charles A. Micchelli
- Yu Zhang
- Yongxin Yang
Papers from Massimiliano Pontil's perspective
Ordered by how strongly the researchers Massimiliano Pontil 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)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Regularized multi--task learning (2004) — 1,664 citations
- Convex multi-task feature learning (2008) — 1,616 citations
- Learning Multiple Tasks with Kernel Methods (2005) — 995 citations
- Empirical Bernstein Bounds and Sample-Variance Penalization (2009) — 619 citations
- Forward and Reverse Gradient-Based Hyperparameter Optimization (2017) — 477 citations
- The Benefit of Multitask Representation Learning (2015) — 422 citations
- Regularization Networks and Support Vector Machines (2000) — 1,338 citations
- Bilevel Programming for Hyperparameter Optimization and Meta-Learning (2018) — 888 citations
- Modelling transition dynamics in MDPs with RKHS embeddings (2012) — 140 citations
- Empirical Risk Minimization under Fairness Constraints (2018) — 500 citations
- Unsupervised Cross-Dataset Transfer Learning for Person Re-identification (2016) — 388 citations
- Sparse coding for multitask and transfer learning (2012) — 195 citations
- Universal Multi-Task Kernels (2008) — 167 citations
- Learning-to-Learn Stochastic Gradient Descent with Biased Regularization (2019) — 120 citations
- Incremental Learning-to-Learn with Statistical Guarantees (2018) — 48 citations
- Regret Bounds for Lifelong Learning (2016) — 61 citations
- An Algorithm for Transfer Learning in a Heterogeneous Environment (2008) — 86 citations
- PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments (2012) — 763 citations
- Oracle Inequalities and Optimal Inference under Group Sparsity (2010) — 405 citations
- Taking Advantage of Sparsity in Multi-Task Learning (2009) — 298 citations