Entropic Mirror Monte Carlo

Anas Cherradi, Yazid Janati, Alain Oliviero Durmus, Sylvain Le Corff, Yohan Petetin, Julien Stoehr
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:19354-19375, 2026.

Abstract

Importance sampling is a Monte Carlo method which designs estimators of expectations under a target distribution using weighted samples from a proposal distribution. When the target distribution is complex, such as multimodal distributions in high-dimensional spaces, the efficiency of importance sampling critically depends on the choice of the proposal distribution. In this paper, we propose a novel adaptive scheme for the construction of efficient proposal distributions. Our algorithm promotes efficient exploration of the target distribution by combining global sampling mechanisms with a delayed weighting procedure. The proposed weighting mechanism plays a key role by enabling rapid resampling in regions where the proposal distribution is poorly adapted to the target. Our sampling algorithm is shown to be geometrically convergent under mild assumptions and is illustrated through various numerical experiments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-cherradi26a, title = {Entropic Mirror {M}onte {C}arlo}, author = {Cherradi, Anas and Janati, Yazid and Oliviero Durmus, Alain and Le Corff, Sylvain and Petetin, Yohan and Stoehr, Julien}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {19354--19375}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/cherradi26a/cherradi26a.pdf}, url = {https://proceedings.mlr.press/v306/cherradi26a.html}, abstract = {Importance sampling is a Monte Carlo method which designs estimators of expectations under a target distribution using weighted samples from a proposal distribution. When the target distribution is complex, such as multimodal distributions in high-dimensional spaces, the efficiency of importance sampling critically depends on the choice of the proposal distribution. In this paper, we propose a novel adaptive scheme for the construction of efficient proposal distributions. Our algorithm promotes efficient exploration of the target distribution by combining global sampling mechanisms with a delayed weighting procedure. The proposed weighting mechanism plays a key role by enabling rapid resampling in regions where the proposal distribution is poorly adapted to the target. Our sampling algorithm is shown to be geometrically convergent under mild assumptions and is illustrated through various numerical experiments.} }
Endnote
%0 Conference Paper %T Entropic Mirror Monte Carlo %A Anas Cherradi %A Yazid Janati %A Alain Oliviero Durmus %A Sylvain Le Corff %A Yohan Petetin %A Julien Stoehr %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-cherradi26a %I PMLR %P 19354--19375 %U https://proceedings.mlr.press/v306/cherradi26a.html %V 306 %X Importance sampling is a Monte Carlo method which designs estimators of expectations under a target distribution using weighted samples from a proposal distribution. When the target distribution is complex, such as multimodal distributions in high-dimensional spaces, the efficiency of importance sampling critically depends on the choice of the proposal distribution. In this paper, we propose a novel adaptive scheme for the construction of efficient proposal distributions. Our algorithm promotes efficient exploration of the target distribution by combining global sampling mechanisms with a delayed weighting procedure. The proposed weighting mechanism plays a key role by enabling rapid resampling in regions where the proposal distribution is poorly adapted to the target. Our sampling algorithm is shown to be geometrically convergent under mild assumptions and is illustrated through various numerical experiments.
APA
Cherradi, A., Janati, Y., Oliviero Durmus, A., Le Corff, S., Petetin, Y. & Stoehr, J.. (2026). Entropic Mirror Monte Carlo. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:19354-19375 Available from https://proceedings.mlr.press/v306/cherradi26a.html.

Related Material