GlassBox Program Synthesis: A Machine Learning Approach
This topic contains 0 replies, has 1 voice, and was last updated by arXiv 1 year, 2 months ago.

GlassBox Program Synthesis: A Machine Learning Approach
Recently proposed models which learn to write computer programs from data use either input/output examples or rich execution traces. Instead, we argue that a novel alternative is to use a glassbox loss function, given as a program itself that can be directly inspected. Glassbox optimization covers a wide range of problems, from computing the greatest common divisor of two integers, to learningtolearn problems. In this paper, we present an intelligent search system which learns, given the partial program and the glassbox problem, the probabilities over the space of programs. We empirically demonstrate that our informed search procedure leads to significant improvements compared to bruteforce program search, both in terms of accuracy and time. For our experiments we use rich context free grammars inspired by number theory, text processing, and algebra. Our results show that (i) performing 4 rounds of our framework typically solves about 70% of the target problems, (ii) our framework can improve itself even in domain agnostic scenarios, and (iii) it can solve problems that would be otherwise too slow to solve with bruteforce search.
GlassBox Program Synthesis: A Machine Learning Approach
by Konstantina Christakopoulou, Adam Tauman Kalai
https://arxiv.org/pdf/1709.08669v1.pdf
You must be logged in to reply to this topic.