Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?
This addresses the challenge of debugging and understanding rare failures in autonomous systems like transportation and robotics, though it appears incremental as it builds on existing normalizing flow methods.
The paper tackles the problem of modeling rare safety-critical failures in autonomous systems with limited data by introducing CalNF, a self-regularized normalizing flow framework, which achieves state-of-the-art performance and enables a case study on the 2022 Southwest Airlines scheduling crisis.
Increased deployment of autonomous systems in fields like transportation and robotics have seen a corresponding increase in safety-critical failures. These failures can be difficult to model and debug due to the relative lack of data: compared to tens of thousands of examples from normal operations, we may have only seconds of data leading up to the failure. This scarcity makes it challenging to train generative models of rare failure events, as existing methods risk either overfitting to noise in the limited failure dataset or underfitting due to an overly strong prior. We address this challenge with CalNF, or calibrated normalizing flows, a self-regularized framework for posterior learning from limited data. CalNF achieves state-of-the-art performance on data-limited failure modeling and inverse problems and enables a first-of-a-kind case study into the root causes of the 2022 Southwest Airlines scheduling crisis.