arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1811.07192cs.LGstat.ML
收藏

遍历推理的理论与算法

The Theory and Algorithm of Ergodic Inference

University of Cambridge(剑桥大学)

Yichuan Zhang

摘要:

近似推理算法是机器学习的基础研究领域之一。机器学习中两个主要的理论推理框架是变分推理(VI)和马尔可夫链蒙特卡罗(MCMC)。然而,由于理论上的根本局限性,如何在计算可扩展性和统计效率上改进现有的VI和MCMC方法是非常具有挑战性的。为了克服这个障碍,我们提出了一个新的理论推理框架称为遍历推理遍历变换的基本性质的基础上。本文的主要贡献是为以后的实际算法的发展奠定了遍历推理的理论基础。

英文摘要:

Approximate inference algorithm is one of the fundamental research fields in machine learning. The two dominant theoretical inference frameworks in machine learning are variational inference (VI) and Markov chain Monte Carlo (MCMC). However, because of the fundamental limitation in the theory, it is very challenging to improve existing VI and MCMC methods on both the computational scalability and statistical efficiency. To overcome this obstacle, we propose a new theoretical inference framework called ergodic Inference based on the fundamental property of ergodic transformations. The key contribution of this work is to establish the theoretical foundation of ergodic inference for the development of practical algorithms in future work.

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。

↑