Dmitry P. Vetrov
Artificial Intelligence · 2006–2022
A researcher in the Science corpus: 24 papers; trusts 2,118 researchers and is trusted by 1,637 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 518 citations into it; #1,138 of 36,961 by trust here, #1,644 by citations
- Computer Vision and Pattern Recognition — 285 citations into it; #1,621 of 21,973 by trust here, #1,427 by citations
- Probabilistic & Bayesian Methods — 151 citations into it; #946 of 1,526 by trust here, #531 by citations
- Optimization & Training — 121 citations into it; #697 of 2,605 by trust here, #443 by citations
- Generative Models — 83 citations into it; #628 of 1,963 by trust here, #1,420 by citations
- Model Architectures — 81 citations into it; #1,583 of 2,288 by trust here, #616 by citations
- Statistics and Probability — 81 citations into it
- Efficiency & Compression — 62 citations into it; #58 of 1,273 by trust here, #154 by citations
Whom Dmitry P. Vetrov trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yoshua Bengio
- Kaiming He
- Yann LeCun
- Radford M. Neal
- Ruslan Salakhutdinov
- Max Welling
- Ilya Sutskever
Who trusts Dmitry P. Vetrov overall
- Pavel Izmailov
- Arsenii Ashukha
- Christos Louizos
- Dmitry Molchanov
- Andrew Gordon Wilson
- Fei Ye
- Alessandro Achille
- Kirill Neklyudov
- Max Welling
- Kumar Shridhar
Papers from Dmitry P. Vetrov's perspective
Ordered by how strongly the researchers Dmitry P. Vetrov 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
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Averaging Weights Leads to Wider Optima and Better Generalization (2018) — 2,084 citations
- Spatially Adaptive Computation Time for Residual Networks (2016) — 382 citations
- Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs (2018) — 951 citations
- Variational Dropout Sparsifies Deep Neural Networks (2017) — 897 citations
- Fast Adaptation in Generative Models with Generative Matching Networks (2016) — 24 citations
- PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions (2015) — 140 citations
- Tensorizing Neural Networks (2015) — 998 citations
- Structured Bayesian Pruning via Log-Normal Multiplicative Noise (2017) — 193 citations
- A Simple Baseline for Bayesian Uncertainty in Deep Learning (2019) — 1,004 citations
- Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning (2020) — 362 citations
- Few-shot Generative Modelling with Generative Matching Networks (2018) — 105 citations
- Ultimate tensorization: compressing convolutional and FC layers alike (2016) — 206 citations
- Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics (2020) — 282 citations
- Doubly Semi-Implicit Variational Inference (2018) — 42 citations
- Variational Autoencoder with Arbitrary Conditioning (2018) — 171 citations
- Subspace Inference for Bayesian Deep Learning (2019) — 164 citations
- Importance Weighted Hierarchical Variational Inference (2019) — 32 citations
- HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement (2022) — 24 citations
- Improving Stability in Deep Reinforcement Learning with Weight Averaging (2018)
- Fast Uncertainty Estimates and Bayesian Model Averaging of DNNs (2018)