A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Cross-Loss Influence Functions to Explain Deep Network Representations
[article]
2022
arXiv
pre-print
As machine learning is increasingly deployed in the real world, it is paramount that we develop the tools necessary to analyze the decision-making of the models we train and deploy to end-users. Recently, researchers have shown that influence functions, a statistical measure of sample impact, can approximate the effects of training samples on classification accuracy for deep neural networks. However, this prior work only applies to supervised learning, where training and testing share an
arXiv:2012.01685v2
fatcat:pqb4vs724ffb3kchszvvptlcoa