Safe CMA-ES (GECCO 2024)

.github/workflows/examples.yml

@@ -23,7 +23,7 @@ jobs:
       - name: Install dependencies
         run: |
           pip install -U pip setuptools
-          pip install --progress-bar off optuna numpy scipy
+          pip install --progress-bar off optuna numpy scipy gpytorch torch
           pip install --progress-bar off -U .
       - run: python examples/quadratic_2d_function.py
       - run: python examples/ipop_cma.py
@@ -34,6 +34,7 @@ jobs:
       - run: python examples/ws_cma.py
       - run: python examples/cma_with_margin_binary.py
       - run: python examples/cma_with_margin_integer.py
+      - run: python examples/safecma.py
   examples-cmawm-without-scipy:
     runs-on: ubuntu-latest
     steps:

.github/workflows/tests.yml

@@ -20,7 +20,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip setuptools
-          pip install --progress-bar off numpy matplotlib scipy mypy flake8 black
+          pip install --progress-bar off numpy matplotlib scipy mypy flake8 black gpytorch torch
       - run: flake8 . --show-source --statistics
       - run: black --check .
       - run: mypy cmaes
@@ -38,7 +38,7 @@ jobs:
           architecture: x64
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip setuptools numpy scipy hypothesis
+          python -m pip install --upgrade pip setuptools numpy scipy hypothesis gpytorch torch
           pip install --progress-bar off .
       - run: python -m unittest
   test-numpy2:
@@ -51,7 +51,7 @@ jobs:
           architecture: x64
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip setuptools scipy hypothesis
+          python -m pip install --upgrade pip setuptools scipy hypothesis gpytorch torch
           python -m pip install --pre --upgrade numpy
           pip install --progress-bar off .
       - run: python -m unittest

README.md

@@ -463,3 +463,4 @@ Rate Adaptation: Can CMA-ES with Default Population Size Solve Multimodal
 and Noisy Problems?, GECCO, 2023.](https://arxiv.org/abs/2304.03473)
 * [Nomura and Shibata 2024] [M. Nomura, M. Shibata, cmaes : A Simple yet Practical Python Library for CMA-ES, arXiv:2402.01373, 2024.](https://arxiv.org/abs/2402.01373)
 * [Ros and Hansen 2008] [R. Ros, N. Hansen, A Simple Modification in CMA-ES Achieving Linear Time and Space Complexity, PPSN, 2008.](https://hal.inria.fr/inria-00287367/document)
+* [Uchida et al. 2024] [K. Uchida, R. Hamano, M. Nomura, S. Saito, S. Shirakawa, CMA-ES for Safe Optimization, GECCO, 2024.](https://arxiv.org/abs/2405.10534)

cmaes/__init__.py

@@ -6,4 +6,9 @@
 from ._dxnesic import DXNESIC  # NOQA
 from ._catcma import CatCMA  # NOQA
 
+try:
+    from ._safe_cma import SafeCMA  # NOQA
+except ImportError:
+    pass  # Implementation of Safe CMA-ES requires scipy, gpytorch, and torch
+
 __version__ = "0.11.1"