Conference item icon

Conference item

Adaptive neural compilation

Abstract:

This paper proposes an adaptive neural-compilation framework to address the problem of efficient program learning. Traditional code optimisation strategies used in compilers are based on applying pre-specified set of transformations that make the code faster to execute without changing its semantics. In contrast, our work involves adapting programs to make them more efficient while considering correctness only on a target input distribution. Our approach is inspired by the recent works on dif...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted manuscript

Actions


Access Document


Files:

Authors


More by this author
Department:
Oxford, MPLS, Engineering Science
More by this author
Department:
Oxford, MPLS, Engineering Science
More by this author
Department:
Oxford, MPLS, Engineering Science
More by this author
Department:
Oxford, MPLS, Engineering Science
More from this funder
Grant:
EPSRC/MURI EP/N019474/1; EP/M013774/1; Programme Grant Seebibyte EP/M013774/1
More from this funder
Grant:
ERC-2012-AdG 321162-HELIOS
Leverhulme Trust More from this funder
Clarendon Fund More from this funder
Publisher:
Neural Information Processing Systems Foundation Publisher's website
Publication date:
2016-10-05
Acceptance date:
2016-05-20
ISSN:
1049-5258
Pubs id:
pubs:656040
URN:
uri:28ab37b9-88f1-48c3-a232-1095c4f894c8
UUID:
uuid:28ab37b9-88f1-48c3-a232-1095c4f894c8
Local pid:
pubs:656040

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP