| PyTorch: An Imperative Style, High-Performance Deep Learning Library A Paszke, S Gross, F Massa, A Lerer, J Bradbury, G Chanan, T Killeen, ... NeurIPS '19: Proceedings of the 33rd International Conference on Neural …, 2019 | 37250* | 2019 |
| ENet: A deep neural network architecture for real-time semantic segmentation A Paszke, A Chaurasia, S Kim, E Culurciello arXiv preprint arXiv:1606.02147, 2016 | 1973 | 2016 |
| An Analysis of Deep Neural Network Models for Practical Applications A Canziani, A Paszke, E Culurciello arXiv preprint arXiv:1605.07678, 2016 | 1353 | 2016 |
| JAX: composable transformations of Python+NumPy programs J Bradbury, R Frostig, P Hawkins, MJ Johnson, C Leary, D Maclaurin, ... http://github.com/google/jax, 2018 | 1207 | 2018 |
| PyTorch Distributed: Experiences on Accelerating Data Parallel Training S Li, Y Zhao, R Varma, O Salpekar, P Noordhuis, T Li, A Paszke, J Smith, ... Proceedings of the VLDB Endowment 13 (12), 3005-3018, 2020 | 235 | 2020 |
| An analysis of deep neural network models for practical applications. arXiv 2016 A Canziani, A Paszke, E Culurciello arXiv preprint arXiv:1605.07678, 2016 | 88 | 2016 |
| PyTorch: An Imperative Style A Paszke, S Gross, F Massa, A Lerer, J Bradbury, G Chanan, T Killeen, ... High-performance deep learning library 12, 1912 | 65 | 1912 |
| Evaluation of neural network architectures for embedded systems A Canziani, E Culurciello, A Paszke 2017 IEEE International Symposium on Circuits and Systems (ISCAS), 1-4, 2017 | 38 | 2017 |
| Getting to the Point. Index Sets and Parallelism-Preserving Autodiff for Pointful Array Programming A Paszke, D Johnson, D Duvenaud, D Vytiniotis, A Radul, M Johnson, ... Proc. ACM Program. Lang. 5 (ICFP), 2021 | 24 | 2021 |
| Decomposing reverse-mode automatic differentiation R Frostig, MJ Johnson, D Maclaurin, A Paszke, A Radul LAFI 2021, 2021 | 10 | 2021 |
| Automap: Towards Ergonomic Automated Parallelism for ML Models M Schaarschmidt, D Grewe, D Vytiniotis, A Paszke, GS Schmid, T Norman, ... ML for Systems (NeurIPS 2021), 2021 | 4 | 2021 |
| VC Density of Set Systems Definable in Tree-Like Graphs A Paszke, M Pilipczuk 45th International Symposium on Mathematical Foundations of Computer Science …, 2020 | 4 | 2020 |
| You only linearize once: Tangents transpose to gradients A Radul, A Paszke, R Frostig, M Johnson, D Maclaurin arXiv preprint arXiv:2204.10923, 2022 | 3 | 2022 |
| Memory-efficient array redistribution through portable collective communication NA Rink, A Paszke, D Vytiniotis, GS Schmid arXiv preprint arXiv:2112.01075, 2021 | 3 | 2021 |
| You Only Linearize Once: Tangents Transpose to Gradients A Radul, A Paszke, R Frostig, MJ Johnson, D Maclaurin Proceedings of the ACM on Programming Languages 7 (POPL), 1246-1274, 2023 | 2 | 2023 |
| Parallelism-preserving automatic differentiation for second-order array languages A Paszke, MJ Johnson, R Frostig, D Maclaurin Proceedings of the 9th ACM SIGPLAN International Workshop on Functional High …, 2021 | 2 | 2021 |
| Parallel Algebraic Effect Handlers N Xie, DD Johnson, D Maclaurin, A Paszke PEPM 2022, 2021 | 1 | 2021 |
| Tensors Fitting Perfectly A Paszke, B Saeta arXiv preprint arXiv:2102.13254, 2021 | 1 | 2021 |
| The Foil: Capture-Avoiding Substitution With No Sharp Edges D Maclaurin, A Radul, A Paszke arXiv preprint arXiv:2210.04729, 2022 | | 2022 |
