Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation
This work addresses the problem of scalable and accurate uncertainty estimation in multi-class classification for machine learning practitioners, representing an incremental improvement over previous approaches.
The paper tackles the trade-off between uncertainty calibration and speed in multi-class Gaussian process classification by introducing a modified softmax likelihood that enables efficient variational inference via data augmentation, achieving well-calibrated uncertainty estimates and competitive predictive performance while being up to two orders faster than state-of-the-art methods.
We propose a new scalable multi-class Gaussian process classification approach building on a novel modified softmax likelihood function. The new likelihood has two benefits: it leads to well-calibrated uncertainty estimates and allows for an efficient latent variable augmentation. The augmented model has the advantage that it is conditionally conjugate leading to a fast variational inference method via block coordinate ascent updates. Previous approaches suffered from a trade-off between uncertainty calibration and speed. Our experiments show that our method leads to well-calibrated uncertainty estimates and competitive predictive performance while being up to two orders faster than the state of the art.