arXiv:2606. 10137v1 Announce Type: new Abstract: A common assumption in strategic classification is that the classifier is public knowledge.
By Ivri Hikri, Nir Rosenfeld
arXiv:2606. 28204v1 Announce Type: cross Abstract: Algorithmic developments in Strategic Classification have been mostly limited to linear classifiers in settings where the best response has a closed-form solution or can be easily approximated.
By Jack Geary, Boyan Gao, Henry Gouk
The paper tackles the single‑machine scheduling problem of minimizing total completion time in a non‑clairvoyant setting, where job processing times are unknown until completion. It introduces a robustness framework that uses a classification model’s confusion matrix to describe uncertainty as permutations within predicted classes, avoiding the computational challenges of traditional robust metrics. The authors present an optimal non‑adaptive strategy for three robust criteria and show that adaptive and randomized algorithms can outperform it when the confusion matrix has certain structural properties.
By Anthony Dugois, Vincent Fagnon, Giorgio Lucarelli
arXiv:2606. 01198v1 Announce Type: new Abstract: Strategic classification studies settings in which agents respond to a deployed classifier by modifying observable features at a cost.
By Siddharth Shrivastava, Mahvith Akshintala, B Vamsha Vardhan Reddy, Naresh Manwani, Sujit Gujar, Ganesh Ghalme
arXiv:2605. 19674v2 Announce Type: replace Abstract: Strategic classification(SC) studies the interaction between decision models and agents who strategically manipulate their features for favorable outcomes.
By Xinpeng Lv, Yunxin Mao, Renzhe Xu, Chunyuan Zheng, Yikai Chen, Haoxuan Li, Yang Shi, Jinxuan Yang, Zhouchen Lin, Yuanlong Chen, Yuanxing Zhang, Shaowu Yang, Wenjing Yang, Haotian Wang
arXiv:2608. 07139v1 Announce Type: new Abstract: Uncertainty quantification is essential when deploying machine learning models in safety-critical applications.
By Joar Skalse, Edoardo Pona, Osvaldo Simeone, Nicola Paoletti