论文标题
从高斯流程中证明可靠的大规模抽样
Provably Reliable Large-Scale Sampling from Gaussian Processes
论文作者
论文摘要
在比较近似高斯过程（GP）模型时，能够从任何GP生成数据可能会有所帮助。如果我们对近似方法的大规模执行感兴趣，我们可能希望生成非常大的合成数据集来评估它们。 naïvely这样做会花费\（\ mathcal {o}（n^3）\）\ \ \（\ Mathcal {o}（n^2）\）内存以生成大小\（n \）示例。我们演示了如何将此类数据生成扩展到大\（n \），同时仍然提供保证，较高的可能性与所需GP的样本无法区分样本。
When comparing approximate Gaussian process (GP) models, it can be helpful to be able to generate data from any GP. If we are interested in how approximate methods perform at scale, we may wish to generate very large synthetic datasets to evaluate them. Naïvely doing so would cost \(\mathcal{O}(n^3)\) flops and \(\mathcal{O}(n^2)\) memory to generate a size \(n\) sample. We demonstrate how to scale such data generation to large \(n\) whilst still providing guarantees that, with high probability, the sample is indistinguishable from a sample from the desired GP.
