Stefano Spigler

Artificial Intelligence · 2016–2020

A researcher in the Science corpus: 10 papers; trusts 83 researchers and is trusted by 10 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 169 citations into it; #32,407 of 35,345 by trust here, #11,750 by citations
• Scaling & Learning Theory — 122 citations into it; #175 of 428 by trust here, #151 by citations
• Optimization & Training — 113 citations into it
• Computer Vision and Pattern Recognition — 62 citations into it
• Statistical and Nonlinear Physics — 56 citations into it
• Materials Chemistry — 51 citations into it; #8,482 of 11,513 by trust here, #7,007 by citations
• AI for Physical Sciences — 46 citations into it
• Model Architectures — 44 citations into it

Whom Stefano Spigler trusts overall

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

1. Yann LeCun
2. Silvio Franz
3. Diederik P. Kingma
4. Christopher K. I. Williams
5. Geoffrey E. Hinton
6. Yoshua Bengio
7. Radford M. Neal
8. Alex Krizhevsky
9. Matthieu Wyart
10. Kaiming He

Who trusts Stefano Spigler overall

1. Mario Geiger
2. Blake Bordelon
3. Abdulkadir Canatar
4. Madhu S. Advani
5. Boris Hanin
6. Arthur Jacot
7. Stéphane d'Ascoli
8. Matthieu Wyart
9. Preetum Nakkiran
10. Bruno Loureiro

Papers from Stefano Spigler's perspective

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

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Scaling description of generalization with number of parameters in deep learning (2019) — 214 citations
• A jamming transition from under- to over-parametrization affects generalization in deep learning (2018) — 160 citations
• Disentangling feature and lazy training in deep neural networks (2019) — 152 citations
• Mean-field avalanches in jammed spheres. (2016) — 44 citations
• Comparing dynamics: deep neural networks versus glassy systems (2018) — 131 citations
• The jamming transition as a paradigm to understand the loss landscape of deep neural networks (2018) — 157 citations
• Asymptotic learning curves of kernel methods: empirical data versus teacher–student paradigm (2020) — 97 citations
• Disentangling feature and lazy learning in deep neural networks: an empirical study (2019) — 17 citations
• Asymptotic learning curves of kernel methods: empirical data v.s. Teacher-Student paradigm (2019) — 43 citations
• A jamming transition from under- to over-parametrization affects loss landscape and generalization (2018) — 59 citations