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
arXiv:2407. 00966v3 Announce Type: replace Abstract: In traditional models of supervised learning, the goal of a learner-- given examples from an arbitrary joint distribution on $\mathbb{R}^d \times \{\pm 1\}$-- is to output a hypothesis that is competitive (to within $\epsilon$) of the best fitting concept from some class.
By Gautam Chandrasekaran, Adam Klivans, Vasilis Kontonis, Raghu Meka, Konstantinos Stavropoulos
arXiv:2607. 13550v1 Announce Type: cross Abstract: Boosting is one of the most successful learning techniques for standard classification and regression tasks.
By R\'emy Chapelle (CESP, CB, EVDG), Nicolas Vayatis (CB), Bruno Falissard (CESP), Mohammed Sedki (CESP)
Boosting is one of the most successful learning techniques for standard classification and regression tasks. Its extension to multi-output prediction problems has found an increasing number of applications in recent years.
arXiv:2605. 18662v2 Announce Type: replace Abstract: Noise-tolerant PAC learning of linear models has been of central interests in machine learning community since the last century.
By Rita Adhikari, Shiwei Zeng
The paper proposes a tensor‑optimization‑powered ensemble method that uses confidence tensors to capture how each weak base classifier performs across different classes. By integrating these tensors and a smooth, partially convex objective that emphasizes margin, the method improves both classification accuracy and generalization while requiring fewer base learners. The authors also prove a property of the loss gradient that enables efficient gradient‑based optimization of the constrained problem.
By Jinghui Yuan, Weijin Jiang, Zhe Cao, Fangyuan Xie, Rong Wang, Feiping Nie, Yuan Yuan