NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:3425
Title:Reliable training and estimation of variance networks

The authors identify problems with estimating predictive variance using neural networks, and propose solutions to fix them. All the reviewers agreed that the paper is well-written, clearly highlighting the limitations of current methods and demonstrating that the proposed solution works better. The reviewers gave some suggestions to improve the paper, and raised some questions about computational complexity and scalability to high dimensions. I encourage the authors to take these into account when they prepare the final version.