Daniel M. Roy
Artificial Intelligence · 2004–2019
A researcher in the Science corpus: 16 papers; trusts 772 researchers and is trusted by 1,030 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 257 citations into it; #1,132 of 36,961 by trust here, #2,185 by citations
- Computer Vision and Pattern Recognition — 100 citations into it; #2,456 of 21,973 by trust here, #3,826 by citations
- Statistics and Probability — 60 citations into it
- Probabilistic & Bayesian Methods — 53 citations into it; #481 of 1,526 by trust here, #265 by citations
- Efficiency & Compression — 47 citations into it
- Optimization & Training — 47 citations into it; #1,261 of 2,605 by trust here, #1,282 by citations
- Statistical Learning Theory — 39 citations into it
- Scaling & Learning Theory — 29 citations into it; #57 of 429 by trust here, #110 by citations
Whom Daniel M. Roy trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Cynthia Dwork
- David A. McAllester
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yann LeCun
- Ruslan Salakhutdinov
- Yoshua Bengio
- Diederik P. Kingma
- Kaiming He
- Max Welling
Who trusts Daniel M. Roy overall
- Behnam Neyshabur
- Pierre Alquier
- Alessandro Achille
- Colin Wei
- Dustin Tran
- Yoshua Bengio
- Srinadh Bhojanapalli
- Ian J. Goodfellow
- Ali Borji
- Gintare Karolina Dziugaite
Papers from Daniel M. Roy's perspective
Ordered by how strongly the researchers Daniel M. Roy 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
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Training generative neural networks via Maximum Mean Discrepancy optimization (2015) — 591 citations
- Church: a language for generative models (2008) — 843 citations
- Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data (2017) — 967 citations
- Linear Mode Connectivity and the Lottery Ticket Hypothesis (2019) — 798 citations
- Mondrian Forests: Efficient Online Random Forests (2014) — 235 citations
- A study of the effect of JPG compression on adversarial images (2016) — 611 citations
- Stabilizing the Lottery Ticket Hypothesis (2019) — 256 citations
- The Lottery Ticket Hypothesis at Scale (2019) — 105 citations
- Mondrian Forests for Large-Scale Regression when Uncertainty Matters (2015) — 60 citations
- Measuring the reliability of MCMC inference with bidirectional Monte Carlo (2016) — 29 citations
- Entropy-SGD optimizes the prior of a PAC-Bayes bound: Data-dependent PAC-Bayes priors via differential privacy (2017) — 160 citations
- Neural Network Matrix Factorization (2015) — 188 citations
- Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates (2019) — 172 citations
- Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors (2017) — 67 citations
- Exact and Approximate Sampling by Systematic Stochastic Search (2009) — 18 citations
- Enhancing Server Availability and Security Through Failure-Oblivious Computing (2004) — 368 citations