2022-06-28-awasthi22c.md

title	booktitle	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
H-Consistency Bounds for Surrogate Loss Minimizers	Proceedings of the 39th International Conference on Machine Learning	We present a detailed study of estimation errors in terms of surrogate loss estimation errors. We refer to such guarantees as H-consistency bounds, since they account for the hypothesis set H adopted. These guarantees are significantly stronger than H-calibration or H-consistency. They are also more informative than similar excess error bounds derived in the literature, when H is the family of all measurable functions. We prove general theorems providing such guarantees, for both the distribution-dependent and distribution-independent settings. We show that our bounds are tight, modulo a convexity assumption. We also show that previous excess error bounds can be recovered as special cases of our general results. We then present a series of explicit bounds in the case of the zero-one loss, with multiple choices of the surrogate loss and for both the family of linear functions and neural networks with one hidden-layer. We further prove more favorable distribution-dependent guarantees in that case. We also present a series of explicit bounds in the case of the adversarial loss, with surrogate losses based on the supremum of the $\rho$-margin, hinge or sigmoid loss and for the same two general hypothesis sets. Here too, we prove several enhancements of these guarantees under natural distributional assumptions. Finally, we report the results of simulations illustrating our bounds and their tightness.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	awasthi22c	0	H-Consistency Bounds for Surrogate Loss Minimizers	1117	1174	1117-1174	1117	false	Awasthi, Pranjal and Mao, Anqi and Mohri, Mehryar and Zhong, Yutao	given family Pranjal Awasthi given family Anqi Mao given family Mehryar Mohri given family Yutao Zhong	2022-06-28		Proceedings of the 39th International Conference on Machine Learning	162	inproceedings	date-parts 2022 6 28	https://proceedings.mlr.press/v162/awasthi22c/awasthi22c.pdf