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 2310.16705cs.LGstat.ML
收藏

变分推断中变分参数空间上的Wasserstein梯度流

Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference

Hokkaido University(北海道大学);University of Tsukuba(茨口大学);Kyoto University(京都大学)

Dai Hai Nguyen, Tetsuya Sakurai, Hiroshi Mamitsuka

AI总结:

本文将变分推断重构为变分参数空间上的概率分布优化问题,提出Wasserstein梯度下降方法,统一了黑箱VI与自然梯度VI,并通过合成数据实验和理论分析验证了其有效性。

摘要:

变分推断(VI)可以表述为一个优化问题,其中调整变分参数以使变分分布与真实后验紧密对齐。该优化任务可以通过黑箱VI中的普通梯度下降或自然梯度VI中的自然梯度下降来处理。在这项工作中,我们将VI重新表述为对定义在变分参数空间上的概率分布的目标函数的优化。随后,我们提出Wasserstein梯度下降来解决这一优化问题。值得注意的是,优化技术,即黑箱VI和自然梯度VI,可以被重新解释为所提出的Wasserstein梯度下降的具体实例。为了提高优化效率,我们开发了数值求解离散梯度流的实用方法。我们通过在合成数据集上的实证实验以及理论分析验证了所提出方法的有效性。

英文摘要:

Variational inference (VI) can be cast as an optimization problem in which the variational parameters are tuned to closely align a variational distribution with the true posterior. The optimization task can be approached through vanilla gradient descent in black-box VI or natural-gradient descent in natural-gradient VI. In this work, we reframe VI as the optimization of an objective that concerns probability distributions defined over a \textit{variational parameter space}. Subsequently, we propose Wasserstein gradient descent for tackling this optimization problem. Notably, the optimization techniques, namely black-box VI and natural-gradient VI, can be reinterpreted as specific instances of the proposed Wasserstein gradient descent. To enhance the efficiency of optimization, we develop practical methods for numerically solving the discrete gradient flows. We validate the effectiveness of the proposed methods through empirical experiments on a synthetic dataset, supplemented by theoretical analyses.

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。

↑