学术文献库

Deep learning is moving towards increasingly sophisticated optimization objectives that employ higher-order functions, such as integration, continuous optimization, and root-finding. Since differentiable programming frameworks such as PyTorch and TensorFlow do not have first-class representations of these functions, developers must reason about the semantics of such objectives and manually translate them to differentiable code. We present a differentiable programming language, $λ_S$, that is the first to deliver a semantics for higher-order functions, higher-order derivatives, and Lipschitz but nondifferentiable functions. Together, these features enable $λ_S$ to expose differentiable, higher-order functions for integration, optimization, and root-finding as first-class functions with automatically computed derivatives. $λ_S$'s semantics is computable, meaning that values can be computed to arbitrary precision, and we implement $λ_S$ as an embedded language in Haskell. We use $λ_S$ to construct novel differentiable libraries for representing probability distributions, implicit surfaces, and generalized parametric surfaces -- all as instances of higher-order datatypes -- and present case studies that rely on computing the derivatives of these higher-order functions and datatypes. In addition to modeling existing differentiable algorithms, such as a differentiable ray tracer for implicit surfaces, without requiring any user-level differentiation code, we demonstrate new differentiable algorithms, such as the Hausdorff distance of generalized parametric surfaces.