๐ฎ
๐ฎ
The Ethereal
Differential Equation Axiomatization: The Impressive Power of Differential Ghosts
February 05, 2018 ยท The Ethereal ยท ๐ Logic in Computer Science
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Andrรฉ Platzer, Yong Kiam Tan
arXiv ID
1802.01226
Category
cs.LO: Logic in CS
Cross-listed
cs.PL,
math.CA,
math.LO
Citations
48
Venue
Logic in Computer Science
Last Checked
1 month ago
Abstract
We prove the completeness of an axiomatization for differential equation invariants. First, we show that the differential equation axioms in differential dynamic logic are complete for all algebraic invariants. Our proof exploits differential ghosts, which introduce additional variables that can be chosen to evolve freely along new differential equations. Cleverly chosen differential ghosts are the proof-theoretical counterpart of dark matter. They create new hypothetical state, whose relationship to the original state variables satisfies invariants that did not exist before. The reflection of these new invariants in the original system then enables its analysis. We then show that extending the axiomatization with existence and uniqueness axioms makes it complete for all local progress properties, and further extension with a real induction axiom makes it complete for all real arithmetic invariants. This yields a parsimonious axiomatization, which serves as the logical foundation for reasoning about invariants of differential equations. Moreover, our results are purely axiomatic, and so the axiomatization is suitable for sound implementation in foundational theorem provers.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Logic in CS
๐ฎ
๐ฎ
The Ethereal
Safe Reinforcement Learning via Shielding
๐ฎ
๐ฎ
The Ethereal
Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
๐ฎ
๐ฎ
The Ethereal
Heterogeneous substitution systems revisited
๐ฎ
๐ฎ
The Ethereal
Omega-Regular Objectives in Model-Free Reinforcement Learning
๐ฎ
๐ฎ
The Ethereal