paper-with-me

Papers

Differentiable Functional Program Interpreters

2016-11-07 · John K. Feser, Marc Brockschmidt, Alexander L. Gaunt, Daniel Tarlow

Programming by Example (PBE) is the task of inducing computer programs from input-output examples. It can be seen as a type of machine learning where the hypothesis space is the set of legal programs in some programming language. Recent work on differentiable interpreters relaxes the discrete space of programs into a continuous space so that search over programs can be performed using gradient-based optimization. While conceptually powerful, so far differentiable interpreter-based program synthesis has only been capable of solving very simple problems. In this work, we study modeling choices that arise when constructing a differentiable programming language and their impact on the success of synthesis. The main motivation for the modeling choices comes from functional programming: we study the effect of memory allocation schemes, immutable data, type systems, and built-in control-flow structures. Empirically we show that incorporating functional programming ideas into differentiable programming languages allows us to learn much more complex programs than is possible with existing differentiable languages.

📄 PDF Abstract BibTeX arXiv:1611.01988

Code (1)

ethancaballero/neural-engineers-first-attempt tf

Tasks

Program Synthesis

Similar Papers 제목 키워드 기반

Towards Neural Functional Program Evaluation

2021-12-09 · NeurIPS Workshop AIPLANS 2021 12 · Torsten Scholak, Jonathan Pilault, Joey Velez-Ginorio

This paper explores the capabilities of current transformer-based language models for program evaluation of simple functional programming languages. We introduce a new program generation mechanism that allows control ove…

Differentiable programming for functional connectomics

2022-05-31 · Rastko Ciric, Armin W. Thomas, Oscar Esteban, Russell A. Poldrack

Mapping the functional connectome has the potential to uncover key insights into brain organisation. However, existing workflows for functional connectomics are limited in their adaptability to new data, and principled w…

Denoising

Improving the Universality and Learnability of Neural Programmer-Interpreters with Combinator Abstraction

2018-02-08 · ICLR 2018 1 · Da Xiao, Jo-Yu Liao, Xingyuan Yuan

To overcome the limitations of Neural Programmer-Interpreters (NPI) in its universality and learnability, we propose the incorporation of combinator abstraction into neural programing and a new NPI architecture to suppor…

Reinforcement Learning

Neural Program Synthesis with a Differentiable Fixer

2020-06-19 · Matej Balog, Rishabh Singh, Petros Maniatis, Charles Sutton

We present a new program synthesis approach that combines an encoder-decoder based synthesis architecture with a differentiable program fixer. Our approach is inspired from the fact that human developers seldom get their…

DecoderProgram Synthesis

Iterative Linear Quadratic Optimization for Nonlinear Control: Differentiable Programming Algorithmic Templates

2022-07-13 · Vincent Roulet, Siddhartha Srinivasa, Maryam Fazel, Zaid Harchaoui

We present the implementation of nonlinear control algorithms based on linear and quadratic approximations of the objective from a functional viewpoint. We present a gradient descent, a Gauss-Newton method, a Newton meth…

Car Racing