Synthesizing Programs with Continuous Optimization
Not on the map. Why?
Abstract (arXiv)
Automatic software generation based on some specification is known as program synthesis. Most existing approaches formulate program synthesis as a search problem with discrete parameters. In this paper, we present a novel formulation of program synthesis as a continuous optimization problem and use a state-of-the-art evolutionary approach, known as Covariance Matrix Adaptation Evolution Strategy to solve the problem. We then propose a mapping scheme to convert the continuous formulation into actual programs. We compare our system, called GENESYS, with several recent program synthesis techniques (in both discrete and continuous domains) and show that GENESYS synthesizes more programs within a fixed time budget than those existing schemes. For example, for programs of length 10, GENESYS synthesizes 28% more programs than those existing schemes within the same time budget.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 61 references that are in the map. First posted on arXiv 2 Nov 2022.
Builds on
24 of 61 references.
References · 24
- 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
- 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
- 2016The CMA Evolution Strategy: A Tutorialcited by 364
- 2017Hierarchical Representations for Efficient Architecture Searchcited by 188
- 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 148
- 2016DeepCoder: Learning to Write Programscited by 145
- 2020AutoML-Zero: Evolving Machine Learning Algorithms From Scratchcited by 137
- 2017RobustFill: Neural Program Learning under Noisy I/Ocited by 124
- 2015Neural Programmer-Interpreterscited by 96
- 2016Neuro-Symbolic Program Synthesiscited by 84
- 2018Leveraging Grammar and Reinforcement Learning for Neural Program Synthesiscited by 83
- 2019Learning to Infer Program Sketchescited by 44
12 more
- 2018Neural-Guided Deductive Search for Real-Time Program Synthesis from Examplescited by 39
- 2017Making Neural Programming Architectures Generalize via Recursioncited by 35
- 2021Latent Execution for Neural Program Synthesiscited by 35
- 2017Program Synthesis using Conflict-Driven Learningcited by 26
- 2018Automatic Program Synthesis of Long Programs with a Learned Garbage Collectorcited by 24
- 2019Synthesizing Datalog Programs Using Numerical Relaxationcited by 23
- 2020Latent Programmer: Discrete Latent Codes for Program Synthesiscited by 18
- 2020Optimal Neural Program Synthesis from Multimodal Specificationscited by 15
- 2018The Three Pillars of Machine Programmingcited by 12
- 2019Learning Fitness Functions for Machine Programmingcited by 5
- 2017AI Programmer: Autonomously Creating Software Programs Using Genetic Algorithmscited by 3
- 2018Relational Program Synthesiscited by 3
Built on by
Citing papers per year: 2023: 2.
2 papers.