Conference item icon

Conference item

DiCE: The infinitely differentiable Monte Carlo estimator

Abstract:

The score function estimator is widely used for estimating gradients of stochastic objectives in stochastic computation graphs (SCG), e.g., in reinforcement learning and meta-learning. While deriving the first order gradient estimators by differentiating a surrogate loss (SL) objective is computationally and conceptually simple, using the same approach for higher order derivatives is more challenging. Firstly, analytically deriving and implementing such estimators is laborious and not complia...

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

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Al-Shedivat, M More by this author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Computer Science
Expand authors...
Engineering and Physical Sciences Research Council More from this funder
Publisher:
Journal of Machine Learning Research Publisher's website
Publication date:
2018-07-03
Acceptance date:
2018-06-12
Pubs id:
pubs:857026
URN:
uri:4cc58c06-d591-498a-9d67-05f359356931
UUID:
uuid:4cc58c06-d591-498a-9d67-05f359356931
Local pid:
pubs:857026

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