Temporal Probability Calibration
This addresses the need for accurate probability estimates in sequential applications like time-series forecasting, though it is incremental as it builds on existing calibration research.
The paper tackled the problem of calibrating class probability estimates from incomplete sequences in sequential data, showing that traditional calibration techniques are insufficient and proposing length-adaptive methods that are substantially more effective across various domains.
In many applications, accurate class probability estimates are required, but many types of models produce poor quality probability estimates despite achieving acceptable classification accuracy. Even though probability calibration has been a hot topic of research in recent times, the majority of this has investigated non-sequential data. In this paper, we consider calibrating models that produce class probability estimates from sequences of data, focusing on the case where predictions are obtained from incomplete sequences. We show that traditional calibration techniques are not sufficiently expressive for this task, and propose methods that adapt calibration schemes depending on the length of an input sequence. Experimental evaluation shows that the proposed methods are often substantially more effective at calibrating probability estimates from modern sequential architectures for incomplete sequences across a range of application domains.