Convergence of Langevin-Simulated Annealing algorithms with multiplicative noise

arXiv link

The notebook simulations-langevin-simulated-annealing.ipynb shows how to use the source code for the experiments.

The file optimizers.py codes the Langevin versions of the usual optimization algorithms.

The machine learning library that is used is TensorFlow.

Citation

Please cite our paper if it helps your research (only arXiv for now):

@ARTICLE{2021arXiv210911669B,
       author = {{Bras}, Pierre and {Pag{\`e}s}, Gilles},
        title = "{Convergence of Langevin-Simulated Annealing algorithms with multiplicative noise}",
      journal = {arXiv e-prints},
     keywords = {Mathematics - Probability},
         year = 2021,
        month = sep,
          eid = {arXiv:2109.11669},
        pages = {arXiv:2109.11669},
archivePrefix = {arXiv},
       eprint = {2109.11669},
 primaryClass = {math.PR},
       adsurl = {https://ui.adsabs.harvard.edu/abs/2021arXiv210911669B},
      adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}