Mario Geiger

Artificial Intelligence · 2017–2022

A researcher in the Science corpus: 18 papers; trusts 279 researchers and is trusted by 41 researchers here, as inferred from the citation graph.

Subfields

Artificial Intelligence — 251 citations into it; #5,198 of 35,345 by trust here, #4,170 by citations
Computer Vision and Pattern Recognition — 143 citations into it; #4,993 of 21,575 by trust here, #4,469 by citations
Materials Chemistry — 136 citations into it; #2,651 of 11,513 by trust here, #4,626 by citations
Scaling & Learning Theory — 132 citations into it; #179 of 428 by trust here, #151 by citations
Optimization & Training — 127 citations into it
Model Architectures — 123 citations into it; #532 of 2,278 by trust here, #621 by citations
Computational Theory and Mathematics — 74 citations into it; #3,904 of 12,182 by trust here, #3,681 by citations
Statistical and Nonlinear Physics — 69 citations into it; #2,534 of 10,127 by trust here, #906 by citations

Whom Mario Geiger trusts overall

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

Who trusts Mario Geiger overall

Papers from Mario Geiger's perspective

Ordered by how strongly the researchers Mario Geiger 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
Attention is All you Need (Neural Information Processing Systems)
Long Short-Term Memory
ImageNet: A large-scale hierarchical image database
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Learning Multiple Layers of Features from Tiny Images

Their papers

Spherical CNNs (2018) — 1,032 citations
Scaling description of generalization with number of parameters in deep learning (2019) — 214 citations
Convolutional Networks for Spherical Signals (2017) — 75 citations
E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials (2021) — 2,192 citations
A jamming transition from under- to over-parametrization affects generalization in deep learning (2018) — 160 citations
A General Theory of Equivariant CNNs on Homogeneous Spaces (2018) — 370 citations
Disentangling feature and lazy training in deep neural networks (2019) — 152 citations
Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks) (2018) — 49 citations
e3nn: Euclidean Neural Networks (2022) — 301 citations
Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties (2020) — 85 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
SE(3)-equivariant prediction of molecular wavefunctions and electronic densities (2021) — 127 citations
Geometric compression of invariant manifolds in neural nets (2020) — 14 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