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
Times are displayed in time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

13:30 - 15:00
The Real WorldResearch Papers at Aurora Borealis
Chair(s): Robert AtkeyUniversity of Strathclyde
13:30
22m
Talk
Demystifying Differentiable Programming: Shift/Reset the Penultimate Backpropagator
Research Papers
Fei Wang, Dan ZhengPurdue University, Google Brain, James Decker, Xilun WuPurdue University, Gregory EssertelPurdue University, Tiark RompfPurdue University
Pre-print
13:52
22m
Talk
Efficient Differentiable Programming in a Functional Array-Processing Language
Research Papers
Amir ShaikhhaUniversity of Oxford, Andrew FitzgibbonMicrosoft Research, Cambridge, Dimitrios VytiniotisDeepMind, Simon Peyton JonesMicrosoft, UK
14:15
22m
Talk
From high-level inference algorithms to efficient code
Research Papers
Rajan WaliaIndiana University, Praveen NarayananIndiana University, USA, Jacques CaretteMcMaster University, Sam Tobin-HochstadtIndiana University, Chung-chieh ShanIndiana University, USA
Pre-print
14:37
22m
Talk
Sound and robust solid modeling via exact real arithmetic and continuityDistinguished Paper
Research Papers
Benjamin ShermanMassachusetts Institute of Technology, USA, Jesse MichelMassachusetts Institute of Technology, Michael CarbinMassachusetts Institute of Technology
DOI Pre-print Media Attached