On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes

Tim G. J. Rudner, Oscar Key, Yarin Gal, Tom Rainforth. On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes. In Marina Meila, Tong Zhang 0001, editors, Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event. Volume 139 of Proceedings of Machine Learning Research, pages 9148-9156, PMLR, 2021. [doi]

Authors

Tim G. J. Rudner

This author has not been identified. Look up 'Tim G. J. Rudner' in Google

Oscar Key

This author has not been identified. Look up 'Oscar Key' in Google

Yarin Gal

This author has not been identified. Look up 'Yarin Gal' in Google

Tom Rainforth

This author has not been identified. Look up 'Tom Rainforth' in Google