EUVIMEDPoznaj EUVIMED
Open access · CC BY-SA 4.0

Distributions for Compositionally Differentiating Parametric Discontinuities

Jesse Michel, Kevin Mu, Xuanda Yang, Sai Praveen Bangaru, Elias Rojas Collins, Gilbert Bernstein, Jonathan Ragan-Kelley, Michael Carbin, Tzu-Mao Li

Proceedings of the ACM on Programming Languages · 2024-04-29 · 8 (OOPSLA1) · 893-922

DOI: 10.1145/3649843 ↗

At a glance

Journal article in Proceedings of the ACM on Programming Languages, published online on 2024-04-29. Written by Jesse Michel and 8 co-authors. Cited 8 times so far (Crossref); 55 references. The full text is freely available (open access, CC BY-SA 4.0). Funded by: NSF.

AbstraktDane bibliograficzneCiteRelated studies

Abstract (original language)

Computations in physical simulation, computer graphics, and probabilistic inference often require the differentiation of discontinuous processes due to contact, occlusion, and changes at a point in time. Popular differentiable programming languages, such as PyTorch and JAX, ignore discontinuities during differentiation. This is incorrect for parametric discontinuities —conditionals containing at least one real-valued parameter and at least one variable of integration. We introduce Potto, the first differentiable first-order programming language to soundly differentiate parametric discontinuities. We present a denotational semantics for programs and program derivatives and show the two accord. We describe the implementation of Potto, which enables separate compilation of programs. Our prototype implementation overcomes previous compile-time bottlenecks achieving an 88.1x and 441.2x speed up in compile time and a 2.5x and 7.9x speed up in runtime, respectively, on two increasingly large image stylization benchmarks. We showcase Potto by implementing a prototype differentiable renderer with separately compiled shaders.

Funding

  • NSF

Cite

APA

Michel, J., Mu, K., Yang, X., Bangaru, S. P., Collins, E. R., Bernstein, G., Ragan-Kelley, J., Carbin, M., & Li, T. (2024). Distributions for Compositionally Differentiating Parametric Discontinuities. Proceedings of the ACM on Programming Languages, 8(OOPSLA1), 893-922. https://doi.org/10.1145/3649843

Vancouver

Michel J, Mu K, Yang X, Bangaru SP, Collins ER, Bernstein G, et al. Distributions for Compositionally Differentiating Parametric Discontinuities. Proceedings of the ACM on Programming Languages. 2024;8(OOPSLA1):893-922. doi:10.1145/3649843

BibTeX
@article{Michel2024,
  author = {Michel, Jesse and Mu, Kevin and Yang, Xuanda and Bangaru, Sai Praveen and Collins, Elias Rojas and Bernstein, Gilbert and Ragan-Kelley, Jonathan and Carbin, Michael and Li, Tzu-Mao},
  title = {Distributions for Compositionally Differentiating Parametric Discontinuities},
  journal = {Proceedings of the ACM on Programming Languages},
  year = {2024},
  volume = {8},
  number = {OOPSLA1},
  pages = {893--922},
  doi = {10.1145/3649843}
}
Start for free →