Christopher De Sa
Artificial Intelligence · with R'e · 2015–2022
A researcher in the Science corpus: 22 papers; trusts 564 researchers and is trusted by 44 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 243 citations into it; #5,044 of 35,345 by trust here, #3,783 by citations
- Computer Vision and Pattern Recognition — 166 citations into it; #7,658 of 21,575 by trust here, #5,287 by citations
- Optimization & Training — 111 citations into it; #872 of 2,601 by trust here, #746 by citations
- Efficiency & Compression — 70 citations into it; #689 of 1,264 by trust here, #788 by citations
- Model Architectures — 55 citations into it
- Natural Language Processing — 47 citations into it; #2,164 of 5,688 by trust here, #1,874 by citations
- Computational Mechanics — 38 citations into it; #3,185 of 10,001 by trust here, #2,942 by citations
- Evaluation & Benchmarks — 27 citations into it
Whom Christopher De Sa trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Yoshua Bengio
- Yann LeCun
- L. Eon Bottou
- Ilya Sutskever
- Karen Simonyan
- Diederik P. Kingma
- X. Zhang
Who trusts Christopher De Sa overall
- Alexander J. Ratner
- Christopher R'e
- Sebastian U. Stich
- Dan Alistarh
- Jakub Konecný
- Tri Dao
- Farzin Haddadpour
- Paroma Varma
- Stephen H. Bach
- Theodoros Rekatsinas
Papers from Christopher De Sa's perspective
Ordered by how strongly the researchers Christopher De Sa trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- 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
- Going deeper with convolutions
Their papers
- Data Programming: Creating Large Training Sets, Quickly (2016) — 780 citations
- PipeMare: Asynchronous Pipeline Parallel DNN Training (2019) — 136 citations
- A Kernel Theory of Modern Data Augmentation (2018) — 225 citations
- Channel Gating Neural Networks (2018) — 207 citations
- Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data (2016) — 26 citations
- Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithms (2015) — 210 citations
- Incremental Knowledge Base Construction Using DeepDive (2015) — 295 citations
- Building Efficient Deep Neural Networks With Unitary Group Convolutions (2018) — 29 citations
- Boosting the Performance of CNN Accelerators with Dynamic Fine-Grained Channel Gating (2019) — 48 citations
- Parallel SGD: When does averaging help? (2016) — 114 citations
- Differentiating through the Fréchet Mean (2020) — 87 citations
- DeepDive: Declarative Knowledge Base Construction (2016) — 155 citations
- High-Accuracy Low-Precision Training (2018) — 114 citations
- GraB: Finding Provably Better Data Permutations than Random Reshuffling (2022) — 21 citations
- Improving Neural Network Quantization without Retraining using Outlier Channel Splitting (2019) — 351 citations
- SysML: The New Frontier of Machine Learning Systems (2019) — 23 citations
- MLSys: The New Frontier of Machine Learning Systems (2019) — 25 citations
- SWALP : Stochastic Weight Averaging in Low-Precision Training (2019) — 107 citations
- Representation Tradeoffs for Hyperbolic Embeddings (2018) — 508 citations
- A Two-pronged Progress in Structured Dense Matrix Vector Multiplication (2018) — 31 citations