Timezone: »

Reliable training and estimation of variance networks
Nicki Skafte · Martin Jørgensen · Søren Hauberg

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #49

We propose and investigate new complementary methodologies for estimating predictive variance networks in regression neural networks. We derive a locally aware mini-batching scheme that results in sparse robust gradients, and we show how to make unbiased weight updates to a variance network. Further, we formulate a heuristic for robustly fitting both the mean and variance networks post hoc. Finally, we take inspiration from posterior Gaussian processes and propose a network architecture with similar extrapolation properties to Gaussian processes. The proposed methodologies are complementary, and improve upon baseline methods individually. Experimentally, we investigate the impact of predictive uncertainty on multiple datasets and tasks ranging from regression, active learning and generative modeling. Experiments consistently show significant improvements in predictive uncertainty estimation over state-of-the-art methods across tasks and datasets.

Author Information

Nicki Skafte (Technical University of Denmark)
Martin Jørgensen (Technical University of Denmark)
Søren Hauberg (Technical University of Denmark)

More from the Same Authors