Concrete Dropout
This addresses the challenge of obtaining reliable uncertainty estimates efficiently for practitioners in vision and reinforcement learning, though it is incremental as it builds on existing dropout methods.
The paper tackled the problem of needing grid-search to tune dropout probabilities for well-calibrated uncertainty in large models, proposing a dropout variant that automatically tunes probabilities, resulting in improved performance and better-calibrated uncertainties across tasks.
Dropout is used as a practical tool to obtain uncertainty estimates in large vision models and reinforcement learning (RL) tasks. But to obtain well-calibrated uncertainty estimates, a grid-search over the dropout probabilities is necessary - a prohibitive operation with large models, and an impossible one with RL. We propose a new dropout variant which gives improved performance and better calibrated uncertainties. Relying on recent developments in Bayesian deep learning, we use a continuous relaxation of dropout's discrete masks. Together with a principled optimisation objective, this allows for automatic tuning of the dropout probability in large models, and as a result faster experimentation cycles. In RL this allows the agent to adapt its uncertainty dynamically as more data is observed. We analyse the proposed variant extensively on a range of tasks, and give insights into common practice in the field where larger dropout probabilities are often used in deeper model layers.