Bayesian Optimization under Stochastic Delayed Feedback
Bayesian optimization (BO) is a widely-used sequential method for zeroth-order optimization of complex and expensive-to-compute black-box functions. The existing BO methods assume that the function evaluation (feedback) is available to the learner immediately or after a fixed delay. Such assumptions may not be practical in many real-life problems like online recommendations, clinical trials, and hyperparameter tuning where feedback is available after a random delay. To benefit from the experimental parallelization in these problems, the learner needs to start new function evaluations without waiting for delayed feedback. In this paper, we consider the BO under stochastic delayed feedback problem. We propose algorithms with sub-linear regret guarantees that efficiently address the dilemma of selecting new function queries while waiting for randomly delayed feedback. Building on our results, we also make novel contributions to batch BO and contextual Gaussian process bandits. Experiments on synthetic and real-life datasets verify the performance of our algorithms.
Code (1)
Tasks
Bayesian OptimizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Stochastic Submodular Bandits with Delayed Composite Anonymous Bandit Feedback
This paper investigates the problem of combinatorial multiarmed bandits with stochastic submodular (in expectation) rewards and full-bandit delayed feedback, where the delayed feedback is assumed to be composite and anon…
Diffusion-Guided Uncertainty-Aware Delayed Policy Optimization
Reinforcement learning in real world environments often suffers from severe performance degradation due to delayed feedback. Existing approaches typically mitigate performance degradation caused by observation delays by …
Reinforcement LearningActivity of any neuron with delayed feedback stimulated with Poisson stream is non-Markov
For a class of excitatory spiking neuron models with delayed feedback fed with a Poisson stochastic process, it is proven that the stream of output interspike intervals cannot be presented as a Markov process of any orde…
Learning Adversarial Markov Decision Processes with Delayed Feedback
Reinforcement learning typically assumes that the agent observes feedback from the environment immediately, but in many real-world applications (like recommendation systems) the feedback is observed in delay. Thus, we co…
Recommendation SystemsBest arm identification in multi-armed bandits with delayed feedback
We propose a generalization of the best arm identification problem in stochastic multi-armed bandits (MAB) to the setting where every pull of an arm is associated with delayed feedback. The delay in feedback increases th…
Hyperparameter OptimizationMulti-Armed Bandits