Divide-and-conquer checkpointing for arbitrary programs with no user annotation
Classical reverse-mode automatic differentiation (AD) imposes only a small constant-factor
overhead in operation count over the original computation, but has storage requirements …
overhead in operation count over the original computation, but has storage requirements …
Efficient implementation of a higher-order language with built-in AD
We show that Automatic Differentiation (AD) operators can be provided in a dynamic
language without sacrificing numeric performance. To achieve this, general forward and …
language without sacrificing numeric performance. To achieve this, general forward and …
Mini-symposium on automatic differentiation and its applications in the financial industry
Automatic differentiation has been involved for long in applied mathematics as an alternative
to finite difference to improve the accuracy of numerical computation of derivatives. Each …
to finite difference to improve the accuracy of numerical computation of derivatives. Each …
AD in Fortran, Part 1: Design
We propose extensions to Fortran which integrate forward and reverse Automatic
Differentiation (AD) directly into the programming model. Irrespective of implementation …
Differentiation (AD) directly into the programming model. Irrespective of implementation …
[PDF][PDF] Pearlmutter & Siskind joint work on Automatic Differentiation (AD)
BA PEARLMUTTER - engineering.purdue.edu
AG Baydin, BA Pearlmutter, AA Radul, and JM Siskind. 2015b. Automatic differentiation in
machine learning: a survey. Technical Report 1502.05767. arxiv. http://arxiv …
machine learning: a survey. Technical Report 1502.05767. arxiv. http://arxiv …
[PDF][PDF] The Differentiable Curry
MARWG Plotkin, DVD Belov - dimitriv.github.io
Differentiable programming allows programmers to calculate program gradients and unlocks
experimentation with new optimizers and neural network architectures. This is why modern …
experimentation with new optimizers and neural network architectures. This is why modern …
[PDF][PDF] AD in Fortran
We propose extensions to FORTRAN which integrate forward and reverse Automatic
Differentiation (AD) directly into the programming model. Irrespective of implementation …
Differentiation (AD) directly into the programming model. Irrespective of implementation …
[PDF][PDF] Thesis title: The Culprit Pointer Method for Selective Backtracking Advisor: David A. McAllester Massachusetts Institute of Technology Ph. D. in computer …
JM Siskind - Consultant, 1987 - engineering.purdue.edu
MetaLogic, Inc. Cambridge, Massachusetts April 1982–August 1985 Founder, Chairman,
Treasurer, Vice President, and CTO Founded MetaLogic to commercialize the MACPITTS …
Treasurer, Vice President, and CTO Founded MetaLogic to commercialize the MACPITTS …