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
Abstract
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.
Ask Lune
Know where this paper stands in minutes, not an afternoon.
Lune can read the top-tier papers that cite it and the ones closest to it, and tells you what it claims, what came after and where it falls short, each point cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
its abstract · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Semantics of Integrating and Differentiating Singularities cites Probabilistic Programming with Programmable Variational Inference
- GradInf: Gradient Estimation as Probabilistic Inference cites Probabilistic Programming with Programmable Variational Inference
Cited by top-tier papers3
- Probabilistic Programming with Programmable Variational InferenceMcCoy R. Becker, Alexander K. Lew, Xiaoyan Wang, Matin Ghavami et al.PLDI 2024 · 8 citations
- Semantics of Integrating and Differentiating SingularitiesJesse Michel, Wonyeol Lee, Hongseok YangPLDI 2025
- GradInf: Gradient Estimation as Probabilistic InferenceGaurav Arya, Mathieu Huot, Moritz Schauer, Alexander K. Lew et al.PLDI 2026
Related papers
- Systematically differentiating parametric discontinuitiesSai Praveen Bangaru, Jesse Michel, Kevin Mu, Gilbert Bernstein et al.SIGGRAPH 2021 · 30 citations
- 𝜆ₛ: computable semantics for differentiable programming with higher-order functions and datatypesBenjamin Sherman, Jesse Michel, Michael CarbinPOPL 2021 · 11 citations
- Aδ: autodiff for discontinuous programs - applied to shadersYuting Yang, Connelly Barnes, Andrew Adams, Adam FinkelsteinSIGGRAPH 2022 · 17 citations
- DiffTaichi: Differentiable Programming for Physical SimulationYuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun et al.ICLR 2020 · 479 citations
- ωPAP Spaces: Reasoning Denotationally About Higher-Order, Recursive Probabilistic and Differentiable ProgramsMathieu Huot, Alexander K. Lew, Vikash K. Mansinghka, Sam StatonLICS 2023 · 5 citations
