Just-in-time learning for bottom-up enumerative synthesis
Just-in-time learning for bottom-up enumerative synthesis
复制标题
自下而上的枚举综合的即时学习
DOI:
10.1145/3428295
复制
发表时间:
2020
影响因子:
--
通讯作者:
Polikarpova, Nadia
中科院分区:
文献类型:
--
作者:
Barke, Shraddha;Peleg, Hila;Polikarpova, Nadia
A key challenge in program synthesis is the astronomical size of the search space the synthesizer has to explore. In response to this challenge, recent work proposed to guide synthesis using learned probabilistic models. Obtaining such a model, however, might be infeasible for a problem domain where no high-quality training data is available. In this work we introduce an alternative approach to guided program synthesis: instead of training a model ahead of time we show how to bootstrap one just in time, during synthesis, by learning from partial solutions encountered along the way. To make the best use of the model, we also propose a new program enumeration algorithm we dub guided bottom-up search, which extends the efficient bottom-up search with guidance from probabilistic models.We implement this approach in a tool called Probe, which targets problems in the popular syntax-guided synthesis (SyGuS) format. We evaluate Probe on benchmarks from the literature and show that it achieves significant performance gains both over unguided bottom-up search and over a state-of-the-art probability-guided synthesizer, which had been trained on a corpus of existing solutions. Moreover, we show that these performance gains do not come at the cost of solution quality: programs generated by Probe are only slightly more verbose than the shortest solutions and perform no unnecessary case-splitting.
登录
查看更多内容
DOI:
--
发表时间:
2018-09
期刊:
--
影响因子:
--
作者:
X. Si;Yuan Yang;H. Dai;M. Naik;Le Song
通讯作者:
X. Si;Yuan Yang;H. Dai;M. Naik;Le Song
DOI:
10.4230/darts.6.2.16
发表时间:
2020
期刊:
2016 IEEE 32nd International Conference on Data Engineering (ICDE)
影响因子:
--
作者:
Hila Peleg;N. Polikarpova
通讯作者:
N. Polikarpova
影响因子:
--
作者:
Xinyu Wang;Işıl Dillig;Rishabh Singh
通讯作者:
Xinyu Wang;Işıl Dillig;Rishabh Singh
影响因子:
--
作者:
Xinyu Wang;Işıl Dillig;Rishabh Singh
通讯作者:
Rishabh Singh
DOI:
--
发表时间:
2016
期刊:
SYNT@CAV
影响因子:
--
作者:
Manos Koukoutos;Etienne Kneuss;Viktor Kunčak
通讯作者:
Viktor Kunčak