Differentiable programming allows for automatically computing derivatives of functions within a high-level language. It has become increasingly popular within the machine learning (ML) community: differentiable programming has been used within backpropagation of neural networks, probabilistic programming, and Bayesian inference. Fundamentally, differentiable programming frameworks empower machine learning and its applications: the availability of efficient and composable automatic differentiation (AD) tools has led to advances in optimization, differentiable simulators, engineering, and science. While AD tools have greatly increased the productivity of ML scientists and practitioners, many problems remain unsolved. Crucially, there is little communication between the broad group of AD users, the programming languages researchers, and the differentiable programming developers, resulting in them working in isolation.
Our workshop aims to provide a forum to narrow the gaps between differentiable and probabilistic languages design, efficient automatic differentiation engines and higher-level applications of differentiable programming. We hope this workshop will harness a closer collaboration between language designers and domain scientists by bringing together a diverse part of the differentiable programming community including people working on core automatic differentiation tools, higher level frameworks that rely upon AD (such as probabilistic programming and differentiable simulators), and applications that use differentiable programs to solve scientific problems.
The explicit goals of the workshop are to:
We are committed to providing a safe, harassment-free, and respectful environment for all participants, in accordance to NeurIPS 2021 Code of Conduct. We have formed a committee for diversity, inclusion and equity (DEI) that is responsible for ensuring that diversity is welcomed at all levels of this workshop, including the organizing committee, invited speakers, and attendees. Our DEI sub-committee is chaired by William Moses, and further consists of Assefaw Gebremedhin and Maria Gorinova.
If you have any feedback, suggestions, questions, or concerns, please reach out to the DEI sub-comittee (emails linked above), the workshop organizer list, or NeurIPShotline@gmail.com. More information on DEI for the whole of NeurIPS can be found at https://neurips.cc/public/DiversityInclusion, with a NeurIPS-wide contact form available here.
For questions or concerns regarding any aspect of the workshop, including the program, speakers, paper submissions, DEI, you may contact the organizers at email@example.com.