TY - GEN
T1 - Multi-fidelity Bayesian optimisation with continuous approximations
AU - Kandasamy, Kirthevasan
AU - Dasarathy, Gautam
AU - Schneider, Jeff
AU - Póczos, Barnabás
PY - 2017/1/1
Y1 - 2017/1/1
N2 - Bandit methods for black-box optimisation, such as Bayesian optimisation, arc used in a variety of applications including hyper-parameter tuning and experiment design. Recently, multi-fidelity methods have garnered considerable attention since function evaluations have become increasingly expensive in such applications. Multi-fidelity methods use cheap approximations to the function of interest to speed up the overall optimisation process. However, most multi-fidelity methods assume only a finite number of approximations. On the other hand, in many practical applications, a continuous spectrum of approximations might be available. For instance, when tuning an expensive neural network, one might choose to approximate the cross validation performance using less data N and/or few training iterations T. Here, the approximations are best viewed as arising out of a continuous two dimensional space (iV, T). In this work, we develop a Bayesian optimisation method, BOCA, for this setting. We characterise its theoretical properties and show that it achieves better regret than than strategies which ignore the approximations. BOCA outperforms several other baselines in synthetic and real experiments.
AB - Bandit methods for black-box optimisation, such as Bayesian optimisation, arc used in a variety of applications including hyper-parameter tuning and experiment design. Recently, multi-fidelity methods have garnered considerable attention since function evaluations have become increasingly expensive in such applications. Multi-fidelity methods use cheap approximations to the function of interest to speed up the overall optimisation process. However, most multi-fidelity methods assume only a finite number of approximations. On the other hand, in many practical applications, a continuous spectrum of approximations might be available. For instance, when tuning an expensive neural network, one might choose to approximate the cross validation performance using less data N and/or few training iterations T. Here, the approximations are best viewed as arising out of a continuous two dimensional space (iV, T). In this work, we develop a Bayesian optimisation method, BOCA, for this setting. We characterise its theoretical properties and show that it achieves better regret than than strategies which ignore the approximations. BOCA outperforms several other baselines in synthetic and real experiments.
UR - http://www.scopus.com/inward/record.url?scp=85048435897&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048435897&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85048435897
T3 - 34th International Conference on Machine Learning, ICML 2017
SP - 2861
EP - 2878
BT - 34th International Conference on Machine Learning, ICML 2017
PB - International Machine Learning Society (IMLS)
T2 - 34th International Conference on Machine Learning, ICML 2017
Y2 - 6 August 2017 through 11 August 2017
ER -