Using semantic distance for diverse and sample efficient genetic programming

David Saxton, Chrisantha Fernando

Keywords: genetic programming, meta learning

TL;DR: We show the importance of diversity in semantic (phenotypic) space when mutating genetic programs, and apply it to learning ML components.

Abstract:

Evolutionary methods, such as genetic programming, search a space of programs to find those with good fitness, often using mutations that manipulate the syntactic structure of programs without being aware of how they affect the semantics. For applications where the semantics are highly sensitive to small syntactic mutations, or where fitness evaluation is expensive, this can make learning programs intractable.

We introduce a mutation operator that yields mutated programs that are semantically far from previously evaluated programs, while still being semantically close to their parent. For function regression, this leads to an algorithm that is one to two orders of magnitude more sample efficient than other gradient-free methods, such as genetic programming, or learning the weights of a neural network using evolutionary strategies.

We show how this method can be applied to learning architecture-specific and general purpose neural network optimizers, and to reinforcement learning loss functions. The learnt components are simple, interpretable, high performance, and contain novel features not seen before such as weight growth.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: General Machine Learning (ie none of the above)