Timezone: »

Asynchronous Batch Bayesian Optimisation with Improved Local Penalisation
Ahsan Alvi · Binxin Ru · Jan-Peter Calliess · Stephen Roberts · Michael A Osborne

Wed Jun 12 11:25 AM -- 11:30 AM (PDT) @ Room 101

Batch Bayesian optimisation (BO) has been successfully applied to hyperparameter tuning using parallel computing, but it is wasteful of resources: workers that complete jobs ahead of others are left idle. We address this problem by developing an approach, Penalising Locally for Asynchronous Bayesian Optimisation on K Workers (PLAyBOOK), for asynchronous parallel BO. We demonstrate empirically the efficacy of PLAyBOOK and its variants on synthetic tasks and a real-world problem. We undertake a comparison between synchronous and asynchronous BO, and show that asynchronous BO often outperforms synchronous batch BO in both wall-clock time and sample efficiency.

Author Information

Ahsan Alvi (University of Oxford)
Binxin Ru (University of Oxford)
Jan-Peter Calliess (University of Oxford)
Stephen Roberts (University of Oxford)
Michael A Osborne (U Oxford)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors