

Adam Paszke
PyTorch and JAX
Writing the autograd everyone uses
Rating
86Impact score
Domains
Automatic differentiationCompilersML frameworks
Scouting report
Wrote the original PyTorch autograd engine as a student and is first author on the PyTorch paper, then moved to Google and became a core author of JAX. Two of the three frameworks serious research runs on have his design decisions inside them, which is an unusual thing to be able to say.
Curator’s note
The differentiation engine under two ecosystems at once.
Portrait
Painted from a photograph of Adam Paszke by Adam Paszke, supplied by the subject.
Sources
- 01PyTorch: An Imperative Style, High-Performance Deep Learning Library (2019) arxiv.org
- 02JAX github.com