Keywords: Rejection, Distributional Robust Optimization, Variational Inference, Density Ratio
TL;DR: We provide an alternative perspective for classification with rejection by learning density ratios.
Abstract: Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions.
The predominant approach is to alter the supervised learning pipeline by augmenting typical loss functions, letting model rejection incur a lower loss than an incorrect prediction.
Instead, we propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance.
This can be formalized via the optimization of a loss's risk with a $ \phi$-divergence regularization term.
Through this idealized distribution, a rejection decision can be made by utilizing the density ratio between this distribution and the data distribution.
We focus on the setting where our $ \phi $-divergences are specified by the family of $ \alpha $-divergence.
Our framework is tested empirically over clean and noisy datasets.
Primary Area: Optimization (convex and non-convex, discrete, stochastic, robust)
Submission Number: 5898
Loading