Symbolic bound tightening over absolute values #251
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Merge from master
Merge from master
Merge from master
Merge from master
Merge from master
Symbolic bound tightening in NLR (NeuralNetworkVerification#249)
ahmed-irfan
reviewed
Apr 27, 2020
|
there are conflicts |
|
Fixed the conflicts |
guykatzz
added a commit
to guykatzz/Marabou
that referenced
this pull request
Apr 27, 2020
Symbolic bound tightening over absolute values (NeuralNetworkVerification#251)
AleksandarZeljic
pushed a commit
to AleksandarZeljic/Marabou
that referenced
this pull request
Oct 9, 2020
…tion#251) * test * basic interval artihmetic bound propagation * another test case * initialize an SBT within the NLR. Pass topology, weights and biases * wip * SBT functionality into NLR * wip * bug fix * cleanup * cleanup * wip * handle eliminated relus * cleanup: remove symbolic bound tightener * oops * additional cleanup * oops * first unit test * unit tests for NLR * basic support for symbolic bound propagations over ABS constraints * unit test - evalue abs + relus * a test for interval bound propagation, for abs constraints * unit tests, and some consequent corrections, to AbsConstraint SBT * set lblb to 0 for both Relu and Abs * always initialize the scalar to 0 by default * consistency * oops Co-authored-by: Guy Katz <guykatz@cs.huji.ac.il>
matanost
pushed a commit
that referenced
this pull request
Nov 2, 2021
* test * basic interval artihmetic bound propagation * another test case * initialize an SBT within the NLR. Pass topology, weights and biases * wip * SBT functionality into NLR * wip * bug fix * cleanup * cleanup * wip * handle eliminated relus * cleanup: remove symbolic bound tightener * oops * additional cleanup * oops * first unit test * unit tests for NLR * basic support for symbolic bound propagations over ABS constraints * unit test - evalue abs + relus * a test for interval bound propagation, for abs constraints * unit tests, and some consequent corrections, to AbsConstraint SBT * set lblb to 0 for both Relu and Abs * always initialize the scalar to 0 by default * consistency * oops Co-authored-by: Guy Katz <guykatz@cs.huji.ac.il>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Teach the network level reasoner to work with AbsoluteValue constraints, and not just ReLUs. One motivating example is to have better support for adversarial robustness queries that use L1 norm.
This is PR #3 in this series