Stochastic Gradient Descent as Approximate Bayesian Inference 论文

2017Journal of Machine Learning Research引用 361

Machine Learning and AlgorithmsMarkov Chains and Monte Carlo MethodsAdvanced Bandit Algorithms Research

人工智能 Machine Learning and Algorithms Advanced Bandit Algorithms Research Markov Chains and Monte Carlo Methods

作者

摘要

Stochastic Gradient Descent with a constant learning rate (constant SGD) simulates a Markov chain with a stationary distribution. With this perspective, we derive several new results. (1) We show t...

作者查看全部 (3)

David M. Blei

Matthew D. Hoffman

Stephan Mandt

Stochastic Gradient Descent as Approximate Bayesian Inference 论文

摘要

作者查看全部 (3)

相关技术查看全部 (3)

相关事件

相关文章