arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.00720stat.MLcs.LG
收藏

大规模高斯过程回归的广义鲁棒贝叶斯委员会机

Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression

Nanyang Technological University(南洋理工大学);Applied Technology Group, Rolls-Royce Singapore(新加坡劳斯莱斯应用技术集团);Data Science and Artificial Intelligence Research Center, Nanyang Technological University(南洋理工大学数据科学与人工智能研究中心)

Haitao Liu, Jianfei Cai, Yi Wang, Yew-Soon Ong

摘要:

为了将标准高斯过程(GP)回归扩展到大规模数据集,聚合模型采用因子分解的训练过程,然后组合来自分布式专家的预测。然而,最先进的聚合模型要么提供不一致的预测,要么需要耗时的聚合过程。我们首先证明了不相交或随机数据划分的典型聚集的不一致性,然后提出了一个一致的,但有效的大规模GP聚集模型。所提出的模型继承了聚合的优点,例如,封闭形式的推理和聚合,并行化和分布式计算。此外,理论和实证分析表明,新的聚合模型表现更好,由于一致的预测,收敛到真正的底层函数时,训练规模接近无穷大。

英文摘要:

In order to scale standard Gaussian process (GP) regression to large-scale datasets, aggregation models employ factorized training process and then combine predictions from distributed experts. The state-of-the-art aggregation models, however, either provide inconsistent predictions or require time-consuming aggregation process. We first prove the inconsistency of typical aggregations using disjoint or random data partition, and then present a consistent yet efficient aggregation model for large-scale GP. The proposed model inherits the advantages of aggregations, e.g., closed-form inference and aggregation, parallelization and distributed computing. Furthermore, theoretical and empirical analyses reveal that the new aggregation model performs better due to the consistent predictions that converge to the true underlying function when the training size approaches infinity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑