Minimum Regret Search for Single- and Multi-Task Optimization

Authors: Jan Hendrik Metzen

ICML 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We provide empirical results both for a synthetic single-task optimization problem as well as for a simulated multi-task robotic control problem.
Researcher Affiliation Collaboration Jan Hendrik Metzen JANMETZEN@MAILBOX.ORG Universit at Bremen, 28359 Bremen, Germany Corporate Research, Robert Bosch Gmb H, 70442 Stuttgart, Germany
Pseudocode No No structured pseudocode or algorithm blocks were found in the paper.
Open Source Code Yes Source code for replicating the reported experiment is available under https://github.com/jmetzen/bayesian_optimization.
Open Datasets No The paper describes generating its own synthetic dataset for the single-task benchmark, and for the multi-task robotic control problem, it uses a simulated environment. There is no concrete access information (link, DOI, citation) provided for a publicly available or open dataset.
Dataset Splits No The paper describes using a set of 250 generated functions for testing and evaluating on '16 test contexts', but it does not specify explicit training/validation/test dataset splits with percentages or sample counts in the traditional sense, as data is acquired sequentially.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running experiments were mentioned in the paper.
Software Dependencies No The paper mentions software components and algorithms like Gaussian processes, RBF and Matérn kernels, DIRECT, L-BFGS, and DMP, but does not provide specific version numbers for any of these software dependencies or libraries.
Experiment Setup Yes Gaussian noise with standard deviation σ = 10 3 is added to each observation. The GP used as surrogate model in the optimizer employed the same isotropic RBF kernel with fixed, identical hyperparameters. ... we used nf = 1000, nr = 25, and ny = 51. ... UCB s exploration parameter κ is set to a constant value of 5.0.