cma

Release 4.4.3

• Addressing issue 231, failures
  in corner cases with large population size, by increasing the step-size
  damping of CSA and TPA. This seems also to improve the performance on
  bbob-f24 in 10 and 20-D while worsening the performance on bbob-f23 in 10 and
  40-D.
• Provide option 'TPA_dampfac' analogous to 'CSA_dampfac'.
• Plots now show the current best solution and the distribution mean in two subplots.
• New:
  • Provide the two (by far) most useful statistical tests with a tidy
    interface in cma.utilities.math.test...
  • Provide a more_algorithms sub-package containing purecma and CompactGA.
  • Provide a provisional experimentation module (requires import cma.experimentation).
• A few smaller fixes and improvements.

Full Changelog: r4.4.2...r4.4.3

Release 4.4.2

• Fix compatibility issues (with comocma):
  • add back the (deprecated) cma.constraints_handling.BoundTransform class
    which was missing since 4.1.0, however, cma.BoundTransform is the
    recommended way to access this class
  • remove dependency of OOOptimizer.optimize on self.result
• fix issue 337 where plotting bails
  with some recent version of matplotlib>3.8.0.
• Various improvements of the logger and plotting.
• Remove default f-offset from binary test functions
  (cma.fitness_functions.binary_foffset = 0 by default now)
• A few new module settings to (better) control corner case behavior.

• Release 4.4.1
  • fmin2 accepts a constraints function as constraints keyword argument
  • an improved CMAEvolutionStrategyResult2 class which also contains the best feasible solution
  • a reset_options method which also clears the current termination status
  • polish the output of .optimize() and of .result_pretty()
  • catch final .stop() value displayed with cma.plot

Release 4.4.0

• constraints handling is available also in the ask-and-tell interface (addressing issues #258, #287, and #167)
• ask can ignore_integer_variables to not mutate integer variables
• an on/off switch for integer centering, cma.integer_centering.centering_on (by default True)
• polishing and minor bug fixes
• code internal:
  • move integer rounding code (applied to delivered solutions) to the cma.transformations.RoundIntegerVariables class
  • utils.SolutionDict can behave like a queue too

Released to PyPI:

• integer variables of candidate solutions are rounded (addressing also issue
  #286)
• moved main docstring from fmin to fmin2
• experimental plots for error estimates and sensitivities
• fix numpy scalar type representations at various places
• replace ineffective use_archives flag with archive_sent_solutions
  and archive_after_sent

Refactor boundary handling code, add BoundDomainTransform stand-alone…

• majorly improved mixed-integer handling based on a more concise lower bound of variances and on so-called integer centering
• moved options and parameters code into a new file
• many small-ish fixes and improvements

see https://github.com/CMA-ES/pycma?tab=readme-ov-file#version-history

Diagonal decoding, fmin functions with surrogate and more.

Smallish fixes and improvements and a constraints use case notebook.

• fixes plot of principal axes which were shown squared by mistake

• constraints handling via a dynamic unconstrained function instantiated from cma.ConstrainedFitnessAL.
• many small improvements and fixes

• fix return value of fmin_con and make it more usable, added attribute best_feasible
• polish evolution_strategy.py
• fix a few smallish bugs

Fix bug when passing args in OOOptimizer.optimize.

• fixed EvalParallel2 from r3.0.1
• EvalParallel2 allows to avoid multiprocessing all together, depending on the value of number_of_processes
• OOOptimizer.optimize can parallelize function calls (using EvalParallel2)

• constraints handling with an Augmented Lagrangian, see cma.fmin_con
• x0 and sigma0 cannot be a string anymore, but x0 may be a callable (a function)
• injections are excluded from negative covariance matrix updates addressing #124
• improved generic Logger, see cma.logger.Logger
• a wrapper as scikit optimizer, use import cma.wrapper
• plotting works now interactively also in a Jupyter notebook
• logger.plot(addcols=1) plots additionally correlation and precision matrices (experimental)
• new tolflatfitness termination option (replaces warnings/errors)
• new tolfunrel termination option (deactivated by default)
• "signals" file is active by default but ignored in verbose=-9 setting
• various other fixes and small improvements

available at PyPI.

• CMADataLogger code moved to its own logger module
• output files go into a separate folder outcmaes by default
• improved matplotlib 3 compatibility
• contour_data and semilogy_signed helper functions
• fitness_transformations.EvalParallel2 class (different interface)
• fitness_models.LQModel introduced

available at PyPI.

The initial solution x0 can be a callable now, which is useful e.g. for the restarted IPOP version.