# Batched Gaussian Process Bandit Optimization via Determinantal Point Processes Source: [Batched Gaussian Process Bandit Optimization via Determinantal Point Processes]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:28:18.594Z Authors: Tarun Kathuria, Amit Deshpande, Pushmeet Kohli Published: 2016-11-13T05:52:58.000Z ## Abstract Gaussian Process bandit optimization has emerged as a powerful tool for optimizing noisy black box functions. One example in machine learning is hyper-parameter optimization where each evaluation of the target function requires training a model which may involve days or even weeks of computation. Most methods for this so-called "Bayesian optimization" only allow sequential exploration of the parameter space. However, it is often desirable to propose batches or sets of parameter values to explore simultaneously, especially when there are large parallel processing facilities at our disposal. Batch methods require modeling the interaction between the different evaluations in the batch, which can be expensive in complex scenarios. In this paper, we propose a new approach for parallelizing Bayesian optimization by modeling the diversity of a batch via Determinantal point processes (DPPs) whose kernels are learned automatically. This allows us to generalize a previous result as well as prove better regret bounds based on DPP sampling. Our experiments on a variety of synthetic and real-world robotics and hyper-parameter optimization tasks indicate that our DPP-based methods, especially those based on DPP sampling, outperform state-of-the-art methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Flowshop Scheduling Problem on FSP-hel2](): Flowshop Scheduling Problem; FSP-hel2; Mean Performance: 142.5. - [Flowshop Scheduling Problem on FSP-reC19](): Flowshop Scheduling Problem; FSP-reC19; Mean Objective Value: 2262. - [Quadratic Assignment Problem on QAP-esc32a](): Quadratic Assignment Problem; QAP-esc32a; Mean Cost: 276.5. - [Traveling Salesman Problem on TSP bayg29](): Traveling Salesman Problem; TSP bayg29; Mean Solution Value: 2727. - [Flowshop Scheduling Problem on FSP-car5](): Flowshop Scheduling Problem; FSP-car5; Mean Objective Value: 7796. - [Quadratic Assignment Problem on QAP-chr12a](): Quadratic Assignment Problem; QAP-chr12a; Mean Cost: 14732. - [Traveling Salesman Problem on TSP burma14](): Traveling Salesman Problem; TSP burma14; Mean Tour Length: 3786. - [Traveling Salesman Problem on TSP-att48](): Traveling Salesman Problem; TSP-att48; Mean Tour Length: 39539. - [Quadratic Assignment Problem on QAPLIB nug instances](): Quadratic Assignment Problem; QAPLIB nug instances; QAP Cost: 3900. ## Original sources and implementation [Original paper]() [PDF]()