λ_S: Computable semantics for differentiable programming with higher-order functions and datatypes

07/15/2020
by   Benjamin Sherman, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset