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 2106.02104cs.LG
收藏

MCMC方案优化的半经验目标函数

Semi-Empirical Objective Functions for MCMC Proposal Optimization

Duke University(杜克大学)

Chris Cannella, Vahid Tarokh

摘要:

目前用于训练神经MCMC建议分布的目标函数隐式地依赖于架构限制来产生合理的优化结果,这阻碍了高度表达的神经MCMC建议架构的开发。在这项工作中,我们介绍并证明了一个半经验的过程,用于确定近似的目标函数,适用于优化任意参数化的建议分布MCMC方法。我们提出的从头算目标函数包括加权组合的功能,其全局最优值和变换不变性的约束,我们认为应该坚持的MCMC效率的一般措施,用于建议优化。我们的实验结果表明,Ab Initio目标函数保持良好的性能和更好的优化行为相比,现有的目标函数的神经MCMC优化。我们发现,Ab Initio目标函数具有足够的鲁棒性,能够对由深度生成网络参数化的神经建议分布进行自信的优化,从而超越传统MCMC方案的范围

英文摘要:

Current objective functions used for training neural MCMC proposal distributions implicitly rely on architectural restrictions to yield sensible optimization results, which hampers the development of highly expressive neural MCMC proposal architectures. In this work, we introduce and demonstrate a semi-empirical procedure for determining approximate objective functions suitable for optimizing arbitrarily parameterized proposal distributions in MCMC methods. Our proposed Ab Initio objective functions consist of the weighted combination of functions following constraints on their global optima and transformation invariances that we argue should be upheld by general measures of MCMC efficiency for use in proposal optimization. Our experimental results demonstrate that Ab Initio objective functions maintain favorable performance and preferable optimization behavior compared to existing objective functions for neural MCMC optimization. We find that Ab Initio objective functions are sufficiently robust to enable the confident optimization of neural proposal distributions parameterized by deep generative networks extending beyond the regimes of traditional MCMC schemes

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。

↑