arXiv:2606. 30136v1 Announce Type: new Abstract: Humans facing algorithmic decision systems have been found to ``game'' them by altering their input data (at a cost to them) in order to favorably change the algorithmic outcomes they receive (at a cost to the algorithm).
By Sura Alhanouti, G\"uzin Bayraksan, Parinaz Naghizadeh
arXiv:2606. 00002v1 Announce Type: new Abstract: Mixed-Integer Linear Programming (MILP) decision engines routinely output nominally optimal plans for high-stakes industrial systems.
By Yi-Xiang Hu
The paper presents a polynomial‑time algorithm for robustly learning Boolean concept classes with respect to a fixed distribution, achieving the optimal error rate of η + ε where η is the noise rate. It builds on Blanc’s earlier, computationally inefficient algorithm and introduces no‑regret learners to overcome the previous limitations. Additionally, the authors provide an efficient method that does not require an ERM oracle for any function class admitting sandwiching polynomials under hypercontractive distributions, including a first polynomial‑time solution for learning halfspaces with Gaussian marginals at error η + ε.
By Adam R. Klivans, Konstantinos Stavropoulos, Sergei Tikhonov, Arsen Vasilyan
Recently, Antoniadis et al. (ICLR 2025) proposed a framework for incorporating predictions to approximate NP-hard selection problems.
The paper investigates binary classification with abstention under separate class‑conditional error constraints, aiming to minimize abstention while keeping both error types below specified thresholds. It derives the distribution‑free minimax rate of excess abstention risk, introduces surrogate‑loss formulations for computational feasibility with models like neural networks, and provides finite‑sample guarantees for excess surrogate ambiguity risk. The authors also formulate the learning task as a constrained optimization problem, analyze its computational complexity in the convex setting, and empirically evaluate the approach against a competing method on several datasets.
By Mohammadreza M. Kalan, Yuyang Deng, Sanaz Hamidi
The paper introduces the concept of observational multiplicity, where multiple probabilistic classifiers can perform similarly yet produce conflicting predictions, undermining interpretability and safety. It proposes measuring this arbitrariness through a regret metric that captures how predictions could shift with different training labels. The authors present a general method to estimate regret, show it varies across dataset groups, and discuss its use for safety via abstention and targeted data collection.
By Erin George, Deanna Needell, Berk Ustun