Write a Blog >>
ICFP 2019
Sun 18 - Fri 23 August 2019 Berlin, Germany
Tue 20 Aug 2019 13:52 - 14:15 at Aurora Borealis - The Real World Chair(s): Robert Atkey

We present a system for the automatic differentiation of a higher-order functional array-processing language. The core functional language underlying this system simultaneously supports both source-to-source automatic differentiation and global optimizations such as loop transformations. Thanks to this feature, we demonstrate how for some real-world machine learning and computer vision benchmarks, the system outperforms the state-of-the-art automatic differentiation tools.

Tue 20 Aug

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

13:30 - 15:00
The Real WorldResearch Papers at Aurora Borealis
Chair(s): Robert Atkey University of Strathclyde
13:30
22m
Talk
Demystifying Differentiable Programming: Shift/Reset the Penultimate Backpropagator
Research Papers
Fei Wang , Dan Zheng Purdue University, Google Brain, James Decker , Xilun Wu Purdue University, Gregory Essertel Purdue University, Tiark Rompf Purdue University
Pre-print
13:52
22m
Talk
Efficient Differentiable Programming in a Functional Array-Processing Language
Research Papers
Amir Shaikhha University of Oxford, Andrew Fitzgibbon Microsoft Research, Cambridge, Dimitrios Vytiniotis DeepMind, Simon Peyton Jones Microsoft, UK
14:15
22m
Talk
From high-level inference algorithms to efficient code
Research Papers
Rajan Walia Indiana University, Praveen Narayanan Indiana University, USA, Jacques Carette McMaster University, Sam Tobin-Hochstadt Indiana University, Chung-chieh Shan Indiana University, USA
Pre-print
14:37
22m
Talk
Sound and robust solid modeling via exact real arithmetic and continuityDistinguished Paper
Research Papers
Benjamin Sherman Massachusetts Institute of Technology, USA, Jesse Michel Massachusetts Institute of Technology, Michael Carbin Massachusetts Institute of Technology
DOI Pre-print Media Attached