Matus Telgarsky

Artificial Intelligence · 2012–2019

A researcher in the Science corpus: 8 papers; trusts 96 researchers and is trusted by 243 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 56 citations into it; #1,105 of 35,345 by trust here, #2,263 by citations
• Optimization & Training — 29 citations into it; #1,282 of 2,601 by trust here, #1,488 by citations
• Computational Mechanics — 19 citations into it; #2,044 of 10,001 by trust here, #1,745 by citations
• Computational Theory and Mathematics — 18 citations into it
• Scaling & Learning Theory — 16 citations into it; #13 of 428 by trust here, #74 by citations
• Computer Vision and Pattern Recognition — 15 citations into it; #3,098 of 21,575 by trust here, #3,459 by citations
• Computational Mathematics — 14 citations into it; #154 of 612 by trust here, #71 by citations
• Statistical Learning Theory — 14 citations into it; #826 of 1,038 by trust here, #744 by citations

Whom Matus Telgarsky trusts overall

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

1. Alex Krizhevsky
2. Yoshua Bengio
3. J. Håstad
4. Peter L. Bartlett
5. Geoffrey E. Hinton
6. Yann LeCun
7. Yurii E. Nesterov
8. Ilya Sutskever
9. Olivier Delalleau
10. Yoav Freund

Who trusts Matus Telgarsky overall

1. Yoav Goldberg
2. Dmitry Yarotsky
3. Quynh N. Nguyen
4. Peter L. Bartlett
5. Nick Harvey
6. Philipp Christian Petersen
7. Yuanbin Cao
8. Or Sharir
9. Difan Zou
10. Quanquan Gu

Papers from Matus Telgarsky's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
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. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Spectrally-normalized margin bounds for neural networks (2017) — 1,473 citations
• Tensor decompositions for learning latent variable models (2012) — 1,214 citations
• Benefits of Depth in Neural Networks (2016) — 707 citations
• Representation Benefits of Deep Feedforward Networks (2015) — 264 citations
• Gradient descent aligns the layers of deep linear networks (2018) — 304 citations
• Risk and parameter convergence of logistic regression (2018) — 142 citations
• Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis (2017) — 592 citations
• The implicit bias of gradient descent on nonseparable data (2019) — 208 citations