Online Distribution Shift Detection via Recency Prediction
This addresses the critical need for reliable distribution shift detection in high-stakes robotic applications, representing an incremental improvement tailored to robotics settings.
The paper tackles the problem of detecting distribution shift in streaming, high-dimensional robotics data by presenting an online method with guarantees on false positive rates, achieving up to 11x faster detection compared to prior work while maintaining low false negative rates in experiments.
When deploying modern machine learning-enabled robotic systems in high-stakes applications, detecting distribution shift is critical. However, most existing methods for detecting distribution shift are not well-suited to robotics settings, where data often arrives in a streaming fashion and may be very high-dimensional. In this work, we present an online method for detecting distribution shift with guarantees on the false positive rate - i.e., when there is no distribution shift, our system is very unlikely (with probability $< ε$) to falsely issue an alert; any alerts that are issued should therefore be heeded. Our method is specifically designed for efficient detection even with high dimensional data, and it empirically achieves up to 11x faster detection on realistic robotics settings compared to prior work while maintaining a low false negative rate in practice (whenever there is a distribution shift in our experiments, our method indeed emits an alert). We demonstrate our approach in both simulation and hardware for a visual servoing task, and show that our method indeed issues an alert before a failure occurs.