2021-07-01-agarwal21c.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations	As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniques for explaining these black boxes in a post hoc manner. In this work, we analyze two popular post hoc interpretation techniques: SmoothGrad which is a gradient based method, and a variant of LIME which is a perturbation based method. More specifically, we derive explicit closed form expressions for the explanations output by these two methods and show that they both converge to the same explanation in expectation, i.e., when the number of perturbed samples used by these methods is large. We then leverage this connection to establish other desirable properties, such as robustness, for these techniques. We also derive finite sample complexity bounds for the number of perturbations required for these methods to converge to their expected explanation. Finally, we empirically validate our theory using extensive experimentation on both synthetic and real-world datasets.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	agarwal21c	0	Towards the Unification and Robustness of Perturbation and Gradient Based Explanations	110	119	110-119	110	false	Agarwal, Sushant and Jabbari, Shahin and Agarwal, Chirag and Upadhyay, Sohini and Wu, Steven and Lakkaraju, Himabindu	given family Sushant Agarwal given family Shahin Jabbari given family Chirag Agarwal given family Sohini Upadhyay given family Steven Wu given family Himabindu Lakkaraju	2021-07-01		Proceedings of the 38th International Conference on Machine Learning	139	inproceedings	date-parts 2021 7 1	http://proceedings.mlr.press/v139/agarwal21c/agarwal21c.pdf