![]() |
![]() |
University of Birmingham > Talks@bham > Theoretical computer science seminar > Automatic differentiation in string diagrams
Automatic differentiation in string diagramsAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Dan Ghica. Reverse-mode automatic differentiation, especially in the presence of complex language features, is notoriously hard to implement correctly, and most implementations focus on differentiating straight-line imperative first-order code. Generalisations exist, however, that can tackle more advanced features; for example, the algorithm described by Pearlmutter and Siskind in their 2008 paper can differentiate higher-order functions written in a pure functional language. We show that AD algorithms can benefit enormously from being translated into the language of string diagrams in two steps: first, we describe a Pearlmutter-Siskind style AD algorithm as a set of rules for transforming hierarchical graphs; rules which can This talk is part of the Theoretical computer science seminar series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsDinner Table Terrorism - Achieving Food Security Seminars on Advanced Materials Type the title of a new list hereOther talks[Friday seminar]: Irradiated brown dwarfs in the desert Many-body localization from Hilbert- and real-space points of view Signatures of structural criticality and universality in the cellular anatomy of the brain The percolating cluster is invisible to image recognition with deep learning Provably Convergent Plug-and-Play Quasi-Newton Methods for Imaging Inverse Problems Topological magnons and quantum magnetism |