Obsidian/Zettelkasten/Literature Notes/A Unified View of Piecewise Linear Neural Network Verification.md

57 lines
1.7 KiB
Markdown

---
authors:
- "Bunel, Rudy R"
- "Turkaslan, Ilker"
- "Torr, Philip"
- "Kohli, Pushmeet"
- "Mudigonda, Pawan K"
citekey: "bunelUnifiedViewPiecewise2018"
publish_date: 2018-01-01
volume: 31
publisher: "Curran Associates, Inc."
last_import: 2025-05-12
---
# Indexing Information
Published: 2018-01
#ToRead
>[!Abstract]
>The success of Deep Learning and its potential use in many safety-critical
applications has motivated research on formal verification of Neural Network
(NN) models. Despite the reputation of learned NN models to behave as black
boxes and the theoretical hardness of proving their properties, researchers
have been successful in verifying some classes of models by exploiting their
piecewise linear structure and taking insights from formal methods such as
Satisifiability Modulo Theory. These methods are however still far from
scaling to realistic neural networks. To facilitate progress on this crucial
area, we make two key contributions. First, we present a unified framework
that encompasses previous methods. This analysis results in the identification
of new methods that combine the strengths of multiple existing approaches,
accomplishing a speedup of two orders of magnitude compared to the previous
state of the art. Second, we propose a new data set of benchmarks which
includes a collection of previously released testcases. We use the benchmark
to provide the first experimental comparison of existing algorithms and
identify the factors impacting the hardness of verification problems.>[!seealso] Related Papers
>
# Annotations
## Notes
![[Paper Notes/A Unified View of Piecewise Linear Neural Network Verification.md]]
## Highlights From Zotero
## Follow-Ups