Timezone: »

Depth Uncertainty Networks for Active Learning
Chelsea Murray · James Allingham · Javier Antorán · José Miguel Hernández-Lobato
Event URL: https://openreview.net/forum?id=GlRdfbA-Mxe »

In active learning, the size and complexity of the training dataset change over time. Simple models that are well specified by the amount of data available at the start of active learning might suffer from bias as more points are actively sampled. Flexible models that might be well suited to the full dataset can suffer from overfitting towards the start of active learning. We tackle this problem using Depth Uncertainty Networks (DUNs), a BNN variant in which the depth of the network, and thus its complexity, is inferred. We find that DUNs outperform other BNN variants on several active learning tasks. Importantly, we show that on the tasks in which DUNs perform best they present notably less overfitting than baselines.

Author Information

Chelsea Murray (University of Cambridge)
James Allingham (University of Cambridge)
Javier Antorán (University of Cambridge)
José Miguel Hernández-Lobato (University of Cambridge)

More from the Same Authors