Write a Blog >>
Tue 21 Jan 2020 10:30 - 11:00 at St Claude - B

Building on the observation that reverse-mode automatic differentiation (AD), a generalisation of backpropagation, can naturally be expressed as pullbacks of differential 1-forms, we design a higher-order, call-by-value functional programming language with a first-class reverse-mode AD operator. Using the category of convenient vector spaces and smooth maps, we show that the operational semantics precisely captures reverse-mode AD, even in a higher-order setting. We exhibit the connection with the differential λ-calculus via a translation that preserves reduction and interpretation.

Tue 21 Jan
Times are displayed in time zone: (GMT-06:00) Saskatchewan, Central America change

10:30 - 12:30: LAFI (né PPS) - B at St Claude
lafi-202010:30 - 11:00
Carol MakUniversity of Oxford, C.-H. Luke OngUniversity of Oxford
lafi-202011:00 - 11:30
Swaraj DashUniversity of Oxford, Sam StatonUniversity of Oxford
File Attached
lafi-202011:30 - 12:00
Jesse SigalUniversity of Edinburgh
lafi-202012:00 - 12:30
Aloïs BrunelDeepomatic, Damiano MazzaCNRS, Michele PaganiIRIF - Université de Paris