Add OmniOptimizer algorithm#791
Open
blankjul wants to merge 4 commits into
Open
Conversation
Implements the Omni-Optimizer (Deb & Tiwari, 2005), a generic EA for single and multi-objective optimization that maintains diversity in both objective and decision variable space. Key components: - Dynamic epsilon for NDS: epsilon_k = (f_k_max - f_k_min) / (N-1), computed per generation to prevent degenerate front splitting - Combined crowding distance: min(CD_F, CD_X), ensuring spread in both objective and variable space simultaneously - OmniRankAndCrowding survival wired into NSGA-II's binary tournament The algorithm correctly finds all 9 Pareto-optimal subsets of OmniTest (n_var=2) where NSGA-II typically misses one or more. Closes #776
Based on evanroyrees' implementation (commits 77a0340..5d7786e). Implements the Omni-Optimizer (Deb & Tiwari, EJOR 2008) with all three components from the paper: - LooseDominator: dynamic per-objective epsilon-dominance whose epsilon is a configurable fraction (delta) of each objective's range - calc_omni_crowding_distance: crowding in both objective and variable space; takes max when above average in either space, min otherwise - NeighborBasedTournamentSelection: restricts mating to nearest neighbors in decision space to preserve distinct Pareto subsets Includes unit tests for each component, registration in no-error and deterministic test suites, and two usage examples.
blankjul
force-pushed
the
feature/omni-optimizer
branch
from
26e55bc to
b2cac93
Compare
|
Looks fine from my perspective. Thank you! |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #776
Based on @evanroyrees' implementation (commits 77a0340..5d7786e) which was already referencing this issue — credit goes to them for the full paper-faithful design. Porting it in here with
omni.pynaming and a small cleanup.What this adds
pymoo/algorithms/moo/omni.py— the Omni-Optimizer (Deb & Tiwari, EJOR 2008), a generic EA that finds and maintains multiple equivalent Pareto-optimal solutions (distinct in decision space, equivalent in objective space). NSGA-II has no variable-space niching and typically collapses to a single Pareto subset.Three components from the paper
1.
LooseDominator— dynamic epsilon-dominancePer-objective epsilon computed every generation as a configurable fraction (
delta) of each objective's range. Solutions closer thandelta * epsilon_jin every objective end up in the same front, preventing over-splitting on flat regions.2.
calc_omni_crowding_distance— combined obj + var space crowdingCrowding is computed independently in objective space and decision variable space. For each individual: if it is less crowded than the front average in either space, take the max; otherwise take the min. This rewards solutions that maintain diversity in at least one space.
3.
NeighborBasedTournamentSelection— restricted matingEach tournament pairs a randomly drawn solution with its nearest neighbor in the (normalized) decision space. Restricting recombination to nearby solutions in X-space biases offspring toward the same region, preserving distinct Pareto subsets.
Result on OmniTest (n_var=2, 9 Pareto subsets, pop=100, gen=150)
Files
pymoo/algorithms/moo/omni.pytests/algorithms/test_omni.pyexamples/algorithms/moo/omni.pyexamples/algorithms/moo/omni_custom.pyHey @lea11100 — this is the implementation you requested in #776. Would you mind having a look and testing it against your use case before we merge? Happy to adjust anything.