Write a Blog >>
ICFP 2018
Sun 23 - Sat 29 September 2018 St. Louis, Missouri, United States
Mon 24 Sep 2018 16:40 - 17:02 at Stifel Theatre - Probabilistic Programming and Learning Chair(s): Michael Sperber

Automatic differentiation (AD) in reverse mode (RAD) is a central component of deep learning and other uses of large-scale optimization. Commonly used RAD algorithms such as backpropagation, however, are complex and stateful, hindering deep understanding, improvement, and parallel execution. This paper develops a simple, generalized AD algorithm calculated from a simple, natural specification. The general algorithm can be specialized by varying the representation of derivatives. In particular, applying well-known constructions to a naive representation yields two RAD algorithms that are far simpler than previously known. In contrast to commonly used RAD implementations, the algorithms defined here involve no graphs, tapes, variables, partial derivatives, or mutation. They are inherently parallel-friendly, correct by construction, and usable directly from an existing programming language with no need for new data types or programming style, thanks to use of an AD-agnostic compiler plugin.

Conal Elliott has been working (and playing) in functional programming for more than 35 years. He especially enjoys applying semantic elegance and rigor to library design and optimized implementation. He invented the paradigm now known as “functional reactive programming” in the early 1990s, and then pioneered compilation techniques for high-performance, high-level embedded domain-specific languages, with applications including 2D and 3D computer graphics. The latter work included the first compilation of Haskell programs to GPU code, while maintaining precise and simple semantics and powerful composability, as well a high degree of optimization. Conal earned a BA in math with honors from the College of Creative Studies at UC Santa Barbara in 1982 and a PhD in Computer Science from Carnegie Mellon University in 1990. He is currently working as distinguished scientist at Target. Previously, we worked at Tabula Inc on chip specification and compiling Haskell to hardware for massively parallel execution. Before Tabula, his positions included Architect at Sun Microsystems and Researcher in the Microsoft Research graphics group. He has also coached couples and led conscious relationship workshops together with his partner Holly Croydon, with whom he now lives on 20 acres in the woods in the California Gold Country.

Mon 24 Sep
Times are displayed in time zone: (GMT-05:00) Guadalajara, Mexico City, Monterrey change

16:40 - 18:10: Research Papers - Probabilistic Programming and Learning at Stifel Theatre
Chair(s): Michael SperberActive Group GmbH
icfp-2018-papers16:40 - 17:02
Conal ElliottTarget, USA
icfp-2018-papers17:02 - 17:25
Adam ŚcibiorUniversity of Cambridge and MPI Tuebingen, Ohad KammarUniversity of Oxford, Zoubin GhahramaniUniversity of Cambridge
icfp-2018-papers17:25 - 17:47
Mitchell WandNortheastern University, USA, Ryan CulpepperCzech Technical University, Theophilos GiannakopoulosBAE Systems, Inc., Andrew CobbNortheastern University
icfp-2018-papers17:47 - 18:10
José Bacelar AlmeiraUniversity of Minho & INESC TEC, Alcino CunhaUniversity of Minho and INESC TEC, Portugal, Nuno MacedoUniversity of Minho & INESC TEC, Hugo PachecoUniversity of Minho, Portugal, José ProençaHASLab/INESC TEC & University of Minho