Milp encoding #288
Merged
Milp encoding #288
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
Symbolic bound tightening in NLR (NeuralNetworkVerification#249)
Symbolic bound tightening over absolute values (NeuralNetworkVerification#251)
Merge from master
Merge from master
Merge from master
…/Marabou into NeuralNetworkVerification-master
Merge from master
Merge from master
performance than non-incremental
wu-haoze
reviewed
Jun 18, 2020
AleksandarZeljic
pushed a commit
to AleksandarZeljic/Marabou
that referenced
this pull request
Oct 9, 2020
* types for PL constraints * first attempt at automatically constructing the NLR * first unit test, couple of bug fixes * use PiecewiseLinearFunctionType * cleanup * some cleanup, and store more information about discovered neurons * wip * complete the construction of the NLR * bug fixes * bug fix * dumping functionality * bug fix * test * changes per Aleks' comments * minor * python bindings * move nlr to separate dir, with namesapce * move neuron index to separate class * basic 'evaluate' functionality for non-consecutive layers * layer class * cleanup * oops * wip * wip * mechanism for extracting the bounds * SBT for weighted sum layers * symbolic bound propagation over a relu layer * fix an issue from the merge * even with master * cleanup * restore cache * oops * wip * oops * move the error handling into the gurobi wrapper * apply valid splits after LP/MILP steps * an incremental mode for solving LP relaxations - achieves better performance than non-incremental * introduced a cutoff mechanism for the LP relaxations * add incremental solving and cutoffs to the MILP formulator * placeholders * Remove faulty ASSERT * new logger stuff * make all 4 kinds of MILP based encoding accessbile through a configuration option * optimize the incremental milp mode Co-authored-by: Guy Katz <guykatz@cs.huji.ac.il>
matanost
pushed a commit
that referenced
this pull request
Nov 2, 2021
* types for PL constraints * first attempt at automatically constructing the NLR * first unit test, couple of bug fixes * use PiecewiseLinearFunctionType * cleanup * some cleanup, and store more information about discovered neurons * wip * complete the construction of the NLR * bug fixes * bug fix * dumping functionality * bug fix * test * changes per Aleks' comments * minor * python bindings * move nlr to separate dir, with namesapce * move neuron index to separate class * basic 'evaluate' functionality for non-consecutive layers * layer class * cleanup * oops * wip * wip * mechanism for extracting the bounds * SBT for weighted sum layers * symbolic bound propagation over a relu layer * fix an issue from the merge * even with master * cleanup * restore cache * oops * wip * oops * move the error handling into the gurobi wrapper * apply valid splits after LP/MILP steps * an incremental mode for solving LP relaxations - achieves better performance than non-incremental * introduced a cutoff mechanism for the LP relaxations * add incremental solving and cutoffs to the MILP formulator * placeholders * Remove faulty ASSERT * new logger stuff * make all 4 kinds of MILP based encoding accessbile through a configuration option * optimize the incremental milp mode 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.
No description provided.