图 书 馆
变分高斯过程Variational Gaussian Process |
|
| 课程网址: | http://videolectures.net/iclr2016_tran_variational_gaussian/ |
| 主讲教师: | Dustin Tran |
| 开课单位: | 哥伦比亚大学 |
| 开课时间: | 2016-05-27 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Variational inference is a powerful tool for approximate inference, and it has been recently applied for representation learning with deep generative models. We develop the variational Gaussian process (VGP), a Bayesian nonparametric variational family, which adapts its shape to match complex posterior distributions. The VGP generates approximate posterior samples by generating latent inputs and warping them through random non-linear mappings; the distribution over random mappings is learned during inference, enabling the transformed outputs to adapt to varying complexity. We prove a universal approximation theorem for the VGP, demonstrating its representative power for learning any model. For inference we present a variational objective inspired by auto-encoders and perform black box inference over a wide class of models. The VGP achieves new state-of-the-art results for unsupervised learning, inferring models such as the deep latent Gaussian model and the recently proposed DRAW. |
| 关 键 词: | 变分推理; 深度模型; 后验分布 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2023-06-07：chenxin01 |
| 最后编审: | 2023-06-07：chenxin01 |
| 阅读次数: | 58 |