Mikhail Belkin
Artificial Intelligence · 2001–2020
A researcher in the Science corpus: 30 papers; trusts 1,079 researchers and is trusted by 5,765 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 434 citations into it; #485 of 36,961 by trust here, #810 by citations
- Computer Vision and Pattern Recognition — 164 citations into it; #628 of 21,973 by trust here, #898 by citations
- Optimization & Training — 164 citations into it; #1,110 of 2,605 by trust here, #1,807 by citations
- Statistical Learning Theory — 93 citations into it; #249 of 1,040 by trust here, #289 by citations
- Statistics and Probability — 89 citations into it; #2,990 of 13,188 by trust here, #2,170 by citations
- Computational Mechanics — 82 citations into it; #654 of 10,021 by trust here, #463 by citations
- Scaling & Learning Theory — 73 citations into it; #61 of 429 by trust here, #70 by citations
- Computational Theory and Mathematics — 71 citations into it; #13 of 12,489 by trust here, #48 by citations
Whom Mikhail Belkin trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Thorsten Joachims
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yoshua Bengio
- Yurii E. Nesterov
- Diederik P. Kingma
- Yann LeCun
- Partha Niyogi
- Kaiming He
- Olivier Chapelle
Who trusts Mikhail Belkin overall
- Yoshua Bengio
- Deng Cai
- Dacheng Tao
- Amit Singer
- Xiaofei He
- Fei Wang
- Matthias Hein
- Shuicheng Yan
- Qiang Yang
- Yi Yang
Papers from Mikhail Belkin's perspective
Ordered by how strongly the researchers Mikhail Belkin 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
- 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
- Laplacian Eigenmaps for Dimensionality Reduction and Data Representation (2003) — 8,581 citations
- Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering (2001) — 5,091 citations
- Reconciling modern machine-learning practice and the classical bias–variance trade-off (2018) — 2,107 citations
- Reconciling modern machine learning and the bias-variance trade-off (2018) — 136 citations
- Semi-Supervised Learning on Riemannian Manifolds (2004) — 894 citations
- The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning (2017) — 334 citations
- To understand deep learning we need to understand kernel learning (2018) — 446 citations
- Beyond the point cloud: from transductive to semi-supervised learning (2005) — 514 citations
- Regularization and Semi-supervised Learning on Large Graphs (2004) — 633 citations
- A Co-Regularization Approach to Semi-supervised Learning with Multiple Views (2005) — 446 citations
- Towards a theoretical foundation for Laplacian-based manifold methods (2005) — 703 citations
- Two models of double descent for weak features (2019) — 413 citations
- Diving into the shallows: a computational perspective on large-scale shallow learning (2017) — 81 citations
- Classification vs regression in overparameterized regimes: Does the loss function matter? (2020) — 172 citations
- Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate (2018) — 280 citations
- Learning privately from multiparty data (2016) — 169 citations
- Does data interpolation contradict statistical optimality? (2018) — 238 citations
- Laplacian Support Vector Machines Trained in the Primal (2009) — 390 citations
- Consistency of spectral clustering (2008) — 423 citations
- On exponential convergence of SGD in non-convex over-parametrized learning (2018) — 112 citations