arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.02666stat.MLcs.LG
收藏

随机梯度算法的变分分析

A Variational Analysis of Stochastic Gradient Algorithms

Columbia University(哥伦比亚大学);Adobe Research(Adobe 研究院)

Stephan Mandt, Matthew D. Hoffman, David M. Blei

摘要:

随机梯度下降(SGD)算法是机器学习中的一种重要算法。在恒定的学习速率下,它是一个随机过程,在初始收敛阶段之后,从平稳分布中生成样本。我们表明,SGD与恒定速率可以有效地用作概率建模的近似后验推理算法。具体来说,我们展示了如何调整SGD的调整参数,例如将所得的平稳分布与后验分布相匹配。该分析依赖于将SGD解释为连续时间随机过程,然后最小化其平稳分布与目标后验之间的库尔贝克-莱布勒散度。(This是符合变分推断的精神的。)更详细地说,我们将SGD建模为多变量Ornstein-Uhlenbeck过程,然后使用该过程的属性来导出最佳参数。这个理论框架还连接SGD到现代可扩展的推理算法,我们分析了最近提出的随机梯度Fisher评分在这个角度下。我们证明了SGD与适当选择的恒定速率提供了一种新的方法来优化概率模型中的超参数。

英文摘要:

Stochastic Gradient Descent (SGD) is an important algorithm in machine learning. With constant learning rates, it is a stochastic process that, after an initial phase of convergence, generates samples from a stationary distribution. We show that SGD with constant rates can be effectively used as an approximate posterior inference algorithm for probabilistic modeling. Specifically, we show how to adjust the tuning parameters of SGD such as to match the resulting stationary distribution to the posterior. This analysis rests on interpreting SGD as a continuous-time stochastic process and then minimizing the Kullback-Leibler divergence between its stationary distribution and the target posterior. (This is in the spirit of variational inference.) In more detail, we model SGD as a multivariate Ornstein-Uhlenbeck process and then use properties of this process to derive the optimal parameters. This theoretical framework also connects SGD to modern scalable inference algorithms; we analyze the recently proposed stochastic gradient Fisher scoring under this perspective. We demonstrate that SGD with properly chosen constant rates gives a new way to optimize hyperparameters in probabilistic models.

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。

↑