Uncertainty Quantification using Generative Approach
This work addresses uncertainty estimation for deep learning practitioners, offering a method compatible with classification and regression tasks, but it appears incremental as it builds on existing generative approaches.
The paper tackles uncertainty quantification in deep neural networks by introducing the Incremental Generative Monte Carlo (IGMC) method, which iteratively trains generative models to compute posterior distributions and provides theoretical convergence guarantees, with empirical validation on MNIST digit classification.
We present the Incremental Generative Monte Carlo (IGMC) method, designed to measure uncertainty in deep neural networks using deep generative approaches. IGMC iteratively trains generative models, adding their output to the dataset, to compute the posterior distribution of the expectation of a random variable. We provide a theoretical guarantee of the convergence rate of IGMC relative to the sample size and sampling depth. Due to its compatibility with deep generative approaches, IGMC is adaptable to both neural network classification and regression tasks. We empirically study the behavior of IGMC on the MNIST digit classification task.