arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.07064stat.MLcs.LGstat.COstat.ME
收藏

使用最大平均偏差的概率测度的最优量化

Optimal quantisation of probability measures using maximum mean discrepancy

Newcastle University(纽卡斯尔大学);Alan Turing Institute(艾伦·图灵研究所);Whisper.ai, Inc.(Whisper.ai公司);King’s College London(伦敦国王学院)

Onur Teymur, Jackson Gorham, Marina Riabiz, Chris. J. Oates

摘要:

几个研究人员已经提出最大平均差异(MMD)的最小化作为量化概率测度的方法,即,以通过代表性点集来近似目标分布。我们考虑顺序算法,greetly最小化MMD在一个离散的候选集。我们提出了一种新的非近视算法,为了提高统计效率和降低计算成本,我们研究了一种变体,该变体在每次迭代时将该技术应用于小批量的候选集。当从目标中采样候选点时,这些新算法及其小批量变体的一致性就建立起来了。我们展示了一系列重要的计算问题的算法,包括优化节点的贝叶斯立方和细化的马尔可夫链输出。

英文摘要:

Several researchers have proposed minimisation of maximum mean discrepancy (MMD) as a method to quantise probability measures, i.e., to approximate a target distribution by a representative point set. We consider sequential algorithms that greedily minimise MMD over a discrete candidate set. We propose a novel non-myopic algorithm and, in order to both improve statistical efficiency and reduce computational cost, we investigate a variant that applies this technique to a mini-batch of the candidate set at each iteration. When the candidate points are sampled from the target, the consistency of these new algorithm - and their mini-batch variants - is established. We demonstrate the algorithms on a range of important computational problems, including optimisation of nodes in Bayesian cubature and the thinning of Markov chain output.

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。

↑