Nikola Konstantinov

Artificial Intelligence · 2018–2020

A researcher in the Science corpus: 4 papers; trusts 96 researchers and is trusted by 10 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 86 citations into it; #15,121 of 35,345 by trust here, #13,544 by citations
• Optimization & Training — 42 citations into it; #2,061 of 2,601 by trust here, #1,365 by citations
• Computer Vision and Pattern Recognition — 33 citations into it
• Safety, Robustness & Interpretability — 19 citations into it
• Computational Mechanics — 15 citations into it; #7,302 of 10,001 by trust here, #2,942 by citations
• Federated & Distributed Learning — 15 citations into it
• Computer Networks and Communications — 14 citations into it; #4,763 of 9,886 by trust here, #8,844 by citations
• Statistics and Probability — 12 citations into it

Whom Nikola Konstantinov trusts overall

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

1. Kaiming He
2. Alex Krizhevsky
3. Shai Ben-David
4. Sergey Ioffe
5. Geoffrey E. Hinton
6. Shai Shalev-Shwartz
7. Mehryar Mohri
8. Christian Szegedy
9. Yoshua Bengio
10. Daryl Pregibon

Who trusts Nikola Konstantinov overall

1. Yishay Mansour
2. Dan Alistarh
3. Mehryar Mohri
4. Elias Frantar
5. Sebastian U. Stich
6. Ananda Theertha Suresh

Papers from Nikola Konstantinov's perspective

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

Their papers

• The Convergence of Sparsified Gradient Methods (2018) — 553 citations
• On the Sample Complexity of Adversarial Multi-Source PAC Learning (2020) — 20 citations
• Robust Learning from Untrusted Sources (2019) — 77 citations
• The Convergence of Stochastic Gradient Descent in Asynchronous Shared Memory (2018) — 42 citations