← Search

Tongtong Fang

2 accepted papers

2023

Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems

NeurIPS 2023spotlight

Distribution shift (DS) may have two levels: the distribution itself changes, and the support (i.e., the set where the probability density is non-zero) also changes. When considering the support change between the training and test distributions, there can be four cases: (i) they exactly match; (ii)…

2020

Rethinking Importance Weighting for Deep Learning under Distribution Shift

NeurIPS 2020spotlight

Under distribution shift (DS) where the training data distribution differs from the test one, a powerful technique is importance weighting (IW) which handles DS in two separate steps: weight estimation (WE) estimates the test-over-training density ratio and weighted classification (WC) trains the cl…