Differentiable Synthesis of Program Architectures

2021-12-01 · NeurIPS 2021 12 · Guofeng Cui, He Zhu

Differentiable programs have recently attracted much interest due to their interpretability, compositionality, and their efficiency to leverage differentiable training. However, synthesizing differentiable programs requires optimizing over a combinatorial, rapidly exploded space of program architectures. Despite the development of effective pruning heuristics, previous works essentially enumerate the discrete search space of program architectures, which is inefficient. We propose to encode program architecture search as learning the probability distribution over all possible program derivations induced by a context-free grammar. This allows the search algorithm to efficiently prune away unlikely program derivations to synthesize optimal program architectures. To this end, an efficient gradient-descent based method is developed to conduct program architecture search in a continuous relaxation of the discrete space of grammar rules. Experiment results on four sequence classification tasks demonstrate that our program synthesizer excels in discovering program architectures that lead to differentiable programs with higher F1 scores, while being more efficient than state-of-the-art program synthesis methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Program Synthesis

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

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…

Decoder Program Synthesis

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 …

Program Synthesis

HOUDINI: Lifelong Learning as Program Synthesis

2018-03-31 · NeurIPS 2018 12 · Lazar Valkov, Dipak Chaudhari, Akash Srivastava, Charles Sutton 외

We present a neurosymbolic framework for the lifelong learning of algorithmic tasks that mix perception and procedural reasoning. Reusing high-level concepts across domains and learning complex procedures are key challen…

Lifelong learning Program Synthesis Transfer Learning

Towards Synthesizing Complex Programs from Input-Output Examples

2017-06-05 · ICLR 2018 1 · Xinyun Chen, Chang Liu, Dawn Song

In recent years, deep learning techniques have been developed to improve the performance of program synthesis from input-output examples. Albeit its significant progress, the programs that can be synthesized by state-of-…

Program Synthesis reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Differentiable Inductive Logic Programming in High-Dimensional Space

2022-08-13 · Stanisław J. Purgał, David M. Cerna, Cezary Kaliszyk

Synthesizing large logic programs through symbolic Inductive Logic Programming (ILP) typically requires intermediate definitions. However, cluttering the hypothesis space with intensional predicates typically degrades pe…

Inductive logic programming Vocal Bursts Intensity Prediction