← Search

T. Yong-Jin Han

2 accepted papers

2021

Deep kernels with probabilistic embeddings for small-data learning

UAI 2021poster

Gaussian Processes (GPs) are known to provide accurate predictions and uncertainty estimates even with small amounts of labeled data by capturing similarity between data points through their kernel function. However traditional GP kernels are not very effective at capturing similarity between high d…

2020

Mix-n-Match : Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning

ICML 2020poster

This paper studies the problem of post-hoc calibration of machine learning classifiers. We introduce the following desiderata for uncertainty calibration: (a) accuracy-preserving, (b) data-efficient, and (c) high expressive power. We show that none of the existing methods satisfy all three requireme…