Learning to Synthesize

Created by W.Langdon from gp-bibliography.bib Revision:1.4504

  author =       "Yingfei Xiong and Bo Wang and Guirong Fu and 
                 Linfei Zang",
  title =        "Learning to Synthesize",
  booktitle =    "GI-2018, ICSE workshops proceedings",
  year =         "2018",
  editor =       "Justyna Petke and Kathryn Stolee and 
                 William B. Langdon and Westley Weimer",
  pages =        "37--44",
  address =      "Gothenburg, Sweden",
  month =        "2 " # jun,
  publisher =    "ACM",
  publisher_address = "New York, NY, USA",
  keywords =     "genetic algorithms, genetic programming, genetic
  isbn13 =       "978-1-4503-5753-1",
  URL =          "http://sei.pku.edu.cn/~xiongyf04/papers/GI18.pdf",
  URL =          "https://arxiv.org/pdf/1802.07608",
  DOI =          "doi:10.1145/3194810.3194816",
  size =         "8 pages",
  abstract =     "n many scenarios we need to find the most likely
                 program under a local context, where the local context
                 can be an incomplete program, a partial specification,
                 natural language description, etc. We call such problem
                 program estimation. In this paper we propose an
                 abstract framework, learning to synthesis, or L2S in
                 short, to address this problem. L2S combines four tools
                 to achieve this: syntax is used to define the search
                 space and search steps, constraints are used to prune
                 off invalid candidates at each search step,
                 machine-learned models are used to estimate conditional
                 probabilities for the candidates at each search step,
                 and search algorithms are used to find the best
                 possible solution. The main goal of L2S is to lay out
                 the design space to motivate the research on program

                 We have performed a preliminary evaluation by
                 instantiating this framework for synthesizing
                 conditions of an automated program repair (APR) system.
                 The training data are from the project itself and
                 related JDK packages. Compared to ACS, a
                 state-of-the-art condition synthesis system for program
                 repair, our approach could deal with a larger search
                 space such that we fixed 4 additional bugs outside the
                 search space of ACS, and relies only on the source code
                 of the current projects.",
  notes =        "is this GP?


                 GI-2018 http://geneticimprovementofsoftware.com part of

Genetic Programming entries for Yingfei Xiong Bo Wang Guirong Fu Linfei Zang