Automatic differentiation in ML: Where we are and where we should be going

10/26/2018
by   Bart van Merriënboer, et al.
0

We review the current state of automatic differentiation (AD) for array programming in machine learning (ML), including the different approaches such as operator overloading (OO) and source transformation (ST) used for AD, graph-based intermediate representations for programs, and source languages. Based on these insights, we introduce a new graph-based intermediate representation (IR) which specifically aims to efficiently support fully-general AD for array programming. Unlike existing dataflow programming representations in ML frameworks, our IR naturally supports function calls, higher-order functions and recursion, making ML models easier to implement. The ability to represent closures allows us to perform AD using ST without a tape, making the resulting derivative (adjoint) program amenable to ahead-of-time optimization using tools from functional language compilers, and enabling higher-order derivatives. Lastly, we introduce a proof of concept compiler toolchain called Myia which uses a subset of Python as a front end.

READ FULL TEXT
research
09/25/2018

Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming

The need to efficiently calculate first- and higher-order derivatives of...
research
10/04/2020

Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients

Applying differentiable programming techniques and machine learning algo...
research
10/12/2021

A Brief Introduction to Automatic Differentiation for Machine Learning

Machine learning and neural network models in particular have been impro...
research
06/06/2018

Efficient Differentiable Programming in a Functional Array-Processing Language

We present a system for the automatic differentiation of a higher-order ...
research
11/10/2016

Efficient Implementation of a Higher-Order Language with Built-In AD

We show that Automatic Differentiation (AD) operators can be provided in...
research
06/27/2021

Automatic Differentiation With Higher Infinitesimals, or Computational Smooth Infinitesimal Analysis in Weil Algebra

We propose an algorithm to compute the C^∞-ring structure of arbitrary W...
research
03/11/2022

GPU Accelerated Automatic Differentiation With Clad

Automatic Differentiation (AD) is instrumental for science and industry....

Please sign up or login with your details

Forgot password? Click here to reset