推论
估计员
上下界
潜变量
可微函数
贝叶斯定理
计算机科学
后验概率
贝叶斯推理
算法
概率逻辑
数学
应用数学
人工智能
贝叶斯概率
统计
数学分析
作者
Diederik P. Kingma,Max Welling
出处
期刊:Cornell University - arXiv
日期:2013-01-01
被引量:1137
标识
DOI:10.48550/arxiv.1312.6114
摘要
How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions are two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods. Second, we show that for i.i.d. datasets with continuous latent variables per datapoint, posterior inference can be made especially efficient by fitting an approximate inference model (also called a recognition model) to the intractable posterior using the proposed lower bound estimator. Theoretical advantages are reflected in experimental results.
科研通智能强力驱动
Strongly Powered by AbleSci AI