Program Synthesis as Latent Continuous Optimization: Evolutionary Search in Neural Embeddings
Created by W.Langdon from
gp-bibliography.bib Revision:1.7954
- @InProceedings{Liskowski:2020:GECCO,
-
author = "Pawel Liskowski and Krzysztof Krawiec and
Nihat Engin Toklu and Jerry Swan",
-
title = "Program Synthesis as Latent Continuous Optimization:
Evolutionary Search in Neural Embeddings",
-
year = "2020",
-
editor = "Carlos Artemio {Coello Coello} and
Arturo Hernandez Aguirre and Josu Ceberio Uribe and
Mario Garza Fabre and Gregorio {Toscano Pulido} and
Katya Rodriguez-Vazquez and Elizabeth Wanner and
Nadarajen Veerapen and Efren Mezura Montes and
Richard Allmendinger and Hugo Terashima Marin and
Markus Wagner and Thomas Bartz-Beielstein and Bogdan Filipic and
Heike Trautmann and Ke Tang and John Koza and
Erik Goodman and William B. Langdon and Miguel Nicolau and
Christine Zarges and Vanessa Volz and Tea Tusar and
Boris Naujoks and Peter A. N. Bosman and
Darrell Whitley and Christine Solnon and Marde Helbig and
Stephane Doncieux and Dennis G. Wilson and
Francisco {Fernandez de Vega} and Luis Paquete and
Francisco Chicano and Bing Xue and Jaume Bacardit and
Sanaz Mostaghim and Jonathan Fieldsend and
Oliver Schuetze and Dirk Arnold and Gabriela Ochoa and
Carlos Segura and Carlos Cotta and Michael Emmerich and
Mengjie Zhang and Robin Purshouse and Tapabrata Ray and
Justyna Petke and Fuyuki Ishikawa and Johannes Lengler and
Frank Neumann",
-
publisher = "Association for Computing Machinery",
-
publisher_address = "New York, NY, USA",
-
booktitle = "Proceedings of the 2020 Genetic and Evolutionary
Computation Conference",
-
pages = "359--367",
-
address = "internet",
-
series = "GECCO '20",
-
month = jul # " 8-12",
-
organisation = "SIGEVO",
-
keywords = "genetic algorithms, genetic programming, autoencoders,
deep learning, embedding, program synthesis",
-
isbn13 = "9781450371285",
-
URL = "https://doi.org/10.1145/3377930.3390213",
-
DOI = "doi:10.1145/3377930.3390213",
-
size = "9 pages",
-
abstract = "In optimization and machine learning, the divide
between discrete and continuous problems and methods is
deep and persistent. We attempt to remove this
distinction by training neural network autoencoders
that embed discrete candidate solutions in continuous
latent spaces. This allows us to take advantage of
state-of-the-art continuous optimization methods for
solving discrete optimisation problems, and mitigates
certain challenges in discrete optimization, such as
design of bias-free search operators. In the
experimental part, we consider program synthesis as the
special case of combinatorial optimization. We train an
autoencoder network on a large sample of programs in a
problem-agnostic, unsupervised manner, and then use it
with an evolutionary continuous optimization algorithm
(CMA-ES) to map the points from the latent space to
programs. We propose also a variant in which
semantically similar programs are more likely to have
similar embeddings. Assessment on a range of benchmarks
in two domains indicates the viability of this approach
and the usefulness of involving program semantics.",
-
notes = "Also known as \cite{10.1145/3377930.3390213}
GECCO-2020 A Recombination of the 29th International
Conference on Genetic Algorithms (ICGA) and the 25th
Annual Genetic Programming Conference (GP)",
- }
Genetic Programming entries for
Pawel Liskowski
Krzysztof Krawiec
Nihat Engin Toklu
Jerry Swan
Citations