Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs

Cheng Wang, Carolin Lawrence, Mathias Niepert

Keywords: uncertainty estimation, calibration, RNN

Abstract: Uncertainty quantification is crucial for building reliable and trustable machine learning systems. We propose to estimate uncertainty in recurrent neural networks (RNNs) via stochastic discrete state transitions over recurrent timesteps. The uncertainty of the model can be quantified by running a prediction several times, each time sampling from the recurrent state transition distribution, leading to potentially different results if the model is uncertain. Alongside uncertainty quantification, our proposed method offers several advantages in different settings. The proposed method can (1) learn deterministic and probabilistic automata from data, (2) learn well-calibrated models on real-world classification tasks, (3) improve the performance of out-of-distribution detection, and (4) control the exploration-exploitation trade-off in reinforcement learning. An implementation is available.

One-sentence Summary: A method to estimate and calibrate uncertainty in recurrent state transitions.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Data: [IMDb Movie Reviews](https://paperswithcode.com/dataset/imdb-movie-reviews)