2025-01-14-shah25a.md

title	booktitle	year	volume	series	month	publisher	pdf	url	software	openreview	abstract	layout	issn	id	tex_title	firstpage	lastpage	page	order	cycles	bibtex_editor	editor	bibtex_author	author	date	address	container-title	genre	issued	extras
Towards Calibrated Losses for Adversarial Robust Reject Option Classification	Proceedings of the 16th Asian Conference on Machine Learning	2025	260	Proceedings of Machine Learning Research	0	PMLR	https://raw.githubusercontent.com/mlresearch/v260/main/assets/shah25a/shah25a.pdf	https://proceedings.mlr.press/v260/shah25a.html	https://github.com/Vrund0212/Calibrated-Losses-for-Adversarial-Robust-Reject-Option-Classification	lx046w4JHs	Robustness towards adversarial attacks is a vital property for classifiers in several applications such as autonomous driving, medical diagnosis, etc. Also, in such scenarios, where the cost of misclassification is very high, knowing when to abstain from prediction becomes crucial. A natural question is which surrogates can be used to ensure learning in scenarios where the input points are adversarially perturbed and the classifier can abstain from prediction? This paper aims to characterize and design surrogates calibrated in "Adversarial Robust Reject Option" setting. First, we propose an adversarial robust reject option loss $\ell_{d}^{\gamma}$ and analyze it for the hypothesis set of linear classifiers $\mathcal{H_\text{lin}}$. Next, we provide a complete characterization result for any surrogate to be $(\ell_{d}^{\gamma},\mathcal{H_{\text{lin}}})$- calibrated. To demonstrate the difficulty in designing surrogates to $\ell_{d}^{\gamma}$, we show negative calibration results for convex surrogates and quasi-concave conditional risk cases (these gave positive calibration in adversarial setting without reject option). We also empirically argue that Shifted Double Ramp Loss (DRL) and Shifted Double Sigmoid Loss (DSL) satisfy the calibration conditions. Finally, we demonstrate the robustness of shifted DRL and shifted DSL against adversarial perturbations on a synthetically generated dataset.	inproceedings	2640-3498	shah25a	Towards Calibrated Losses for Adversarial Robust Reject Option Classification	1256	1271	1256-1271	1256	false	Nguyen, Vu and Lin, Hsuan-Tien	given family Vu Nguyen given family Hsuan-Tien Lin	Shah, Vrund and Chaudhari, Tejas Kiran and Manwani, Naresh	given family Vrund Shah given family Tejas Kiran Chaudhari given family Naresh Manwani	2025-01-14		Proceedings of the 16th Asian Conference on Machine Learning	inproceedings	date-parts 2025 1 14	label link Supplementary PDF https://raw.githubusercontent.com/mlresearch/v260/main/assets/assets/shah25a/shah25a-supp.pdf