Mikhail Khodak

Artificial Intelligence · 2018–2021

A researcher in the Science corpus: 8 papers; trusts 361 researchers and is trusted by 39 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 548 citations into it; #5,816 of 35,345 by trust here, #2,163 by citations
• Federated & Distributed Learning — 137 citations into it
• Optimization & Training — 130 citations into it; #1,067 of 2,601 by trust here, #1,154 by citations
• Computer Vision and Pattern Recognition — 123 citations into it; #10,329 of 21,575 by trust here, #5,565 by citations
• Representation & Self-Supervised Learning — 77 citations into it; #2,768 of 3,145 by trust here, #1,246 by citations
• Computer Networks and Communications — 67 citations into it
• Efficiency & Compression — 56 citations into it
• Natural Language Processing — 48 citations into it

Whom Mikhail Khodak trusts overall

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

1. Geoffrey E. Hinton
2. Alex Krizhevsky
3. Yoshua Bengio
4. Kaiming He
5. Yann LeCun
6. Ilya Sutskever
7. Diederik P. Kingma
8. Jonathan Baxter
9. Chelsea Finn
10. Elad Hazan

Who trusts Mikhail Khodak overall

1. Alireza Fallah
2. Jeffrey Li
3. Aryan Mokhtari
4. Filip Hanzely
5. Sebastian Flennerhag
6. Nilesh Tripuraneni
7. Daliang Li
8. Nikunj Saunshi
9. Timo Schick
10. Ameet Talwalkar

Papers from Mikhail Khodak's perspective

Ordered by how strongly the researchers Mikhail Khodak 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. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• A Theoretical Analysis of Contrastive Unsupervised Representation Learning (2019) — 910 citations
• Provable Guarantees for Gradient-Based Meta-Learning (2019) — 163 citations
• Advances and Open Problems in Federated Learning (2019) — 9,019 citations
• Adaptive Gradient-Based Meta-Learning Methods (2019) — 397 citations
• A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors (2018) — 109 citations
• Differentially Private Meta-Learning (2019) — 127 citations
• Initialization and Regularization of Factorized Neural Layers (2021) — 78 citations
• A Sample Complexity Separation between Non-Convex and Convex Meta-Learning (2020) — 32 citations