Timezone: »
When Gödel discovered Automatic Differentiation - Marie Kerjean - Centre national de la recherche scientifique
AIPLANS 2021
Tue Dec 14 05:00 AM -- 06:00 AM (PST) @
I will explore the boundaries between differentiable programming and logic, through the prism of the Curry-Howard correspondence. I will recall the latter and explain how automatic differentiation fits into each of its three facets: functions, proofs and programs. In particular, I will explain how backpropagation is identified with Gödel's Dialectica translation, a transformation of logical formulas historically used to prove consistency theorems and widely used in proof theory since then.
Author Information
AIPLANS 2021 (NeurIPS)
More from the Same Authors
-
2021 : Program Synthesis »
AIPLANS 2021 -
2021 : Automatic Differentiation »
AIPLANS 2021 -
2021 : Neurosymbolic Systems and Reasoning »
AIPLANS 2021 -
2021 : Theorem Proving and Formal Mathematics »
AIPLANS 2021 -
2021 : Programming Languages Theory »
AIPLANS 2021 -
2021 : Poster Session »
AIPLANS 2021 -
2021 : Type Inference as Optimization - Eirene V. Pandi »
AIPLANS 2021 · Eirini V. Pandi -
2021 : Learning Adaptive Control Flow in Transformers for Improved Systematic Generalization - Róbert Csordás »
AIPLANS 2021 · Róbert Csordás -
2021 : Learning Rules with Stratified Negation in Differentiable ILP - Giri Krishnan »
AIPLANS 2021 · Giri Krishnan -
2021 : LazyPPL: laziness and types in non-parametric probabilistic programs - Hugo Paquet »
AIPLANS 2021 · Hugo Paquet -
2021 : Meta-Learning an Inference Algorithm for Probabilistic Programs - Gwonsoo Che »
AIPLANS 2021 · Gwonsoo Che -
2021 : Dependent Types for Machine Learning in Dex - David Duvenaud - University of Toronto »
David Duvenaud · AIPLANS 2021