Adaptive MCMC with Bayesian Optimization

Nimalan Mahendran, Ziyu Wang, Firas Hamze, Nando De Freitas
; Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, PMLR 22:751-760, 2012.

Abstract

This paper proposes a new randomized strategy for adaptive MCMC using Bayesian optimization. This approach applies to non-differentiable objective functions and trades off exploration and exploitation to reduce the number of potentially costly objective function evaluations. We demonstrate the strategy in the complex setting of sampling from constrained, discrete and densely connected probabilistic graphical models where, for each variation of the problem, one needs to adjust the parameters of the proposal mechanism automatically to ensure efficient mixing of the Markov chains.

Cite this Paper


BibTeX
@InProceedings{pmlr-v22-mahendran12, title = {Adaptive MCMC with Bayesian Optimization}, author = {Nimalan Mahendran and Ziyu Wang and Firas Hamze and Nando De Freitas}, booktitle = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics}, pages = {751--760}, year = {2012}, editor = {Neil D. Lawrence and Mark Girolami}, volume = {22}, series = {Proceedings of Machine Learning Research}, address = {La Palma, Canary Islands}, month = {21--23 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v22/mahendran12/mahendran12.pdf}, url = {http://proceedings.mlr.press/v22/mahendran12.html}, abstract = {This paper proposes a new randomized strategy for adaptive MCMC using Bayesian optimization. This approach applies to non-differentiable objective functions and trades off exploration and exploitation to reduce the number of potentially costly objective function evaluations. We demonstrate the strategy in the complex setting of sampling from constrained, discrete and densely connected probabilistic graphical models where, for each variation of the problem, one needs to adjust the parameters of the proposal mechanism automatically to ensure efficient mixing of the Markov chains.} }
Endnote
%0 Conference Paper %T Adaptive MCMC with Bayesian Optimization %A Nimalan Mahendran %A Ziyu Wang %A Firas Hamze %A Nando De Freitas %B Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2012 %E Neil D. Lawrence %E Mark Girolami %F pmlr-v22-mahendran12 %I PMLR %J Proceedings of Machine Learning Research %P 751--760 %U http://proceedings.mlr.press %V 22 %W PMLR %X This paper proposes a new randomized strategy for adaptive MCMC using Bayesian optimization. This approach applies to non-differentiable objective functions and trades off exploration and exploitation to reduce the number of potentially costly objective function evaluations. We demonstrate the strategy in the complex setting of sampling from constrained, discrete and densely connected probabilistic graphical models where, for each variation of the problem, one needs to adjust the parameters of the proposal mechanism automatically to ensure efficient mixing of the Markov chains.
RIS
TY - CPAPER TI - Adaptive MCMC with Bayesian Optimization AU - Nimalan Mahendran AU - Ziyu Wang AU - Firas Hamze AU - Nando De Freitas BT - Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics PY - 2012/03/21 DA - 2012/03/21 ED - Neil D. Lawrence ED - Mark Girolami ID - pmlr-v22-mahendran12 PB - PMLR SP - 751 DP - PMLR EP - 760 L1 - http://proceedings.mlr.press/v22/mahendran12/mahendran12.pdf UR - http://proceedings.mlr.press/v22/mahendran12.html AB - This paper proposes a new randomized strategy for adaptive MCMC using Bayesian optimization. This approach applies to non-differentiable objective functions and trades off exploration and exploitation to reduce the number of potentially costly objective function evaluations. We demonstrate the strategy in the complex setting of sampling from constrained, discrete and densely connected probabilistic graphical models where, for each variation of the problem, one needs to adjust the parameters of the proposal mechanism automatically to ensure efficient mixing of the Markov chains. ER -
APA
Mahendran, N., Wang, Z., Hamze, F. & Freitas, N.D.. (2012). Adaptive MCMC with Bayesian Optimization. Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, in PMLR 22:751-760

Related Material