arXiv:2610. 10383v1 Announce Type: new Abstract: Boosting converts weak hypotheses with a small edge over random guessing into highly accurate predictors, but the expressive power of the resulting classifier can depend strongly on the structure of the base class.
Boosting converts weak hypotheses with a small edge over random guessing into highly accurate predictors, but the expressive power of the resulting classifier can depend strongly on the structure of t...
arXiv:2610. 31890v1 Announce Type: new Abstract: We study the PAC-learnability of function classes that map inputs to probability distributions over a finite space.
arXiv:2607. 05791v1 Announce Type: cross Abstract: Boosting is a fundamental technique for generically improving the accuracy of learning algorithms (Schapire 1989).
The paper introduces a statistical learning theory for size generalization in models that handle variable-size structured data such as sets and graphs. It proves an exponential separation in sample complexity: polynomial in-domain learning yields only logarithmic decay in size-generalization error, while an exponential source condition restores polynomial decay. These results provide dimension‑free scaling laws and optimal minimax bounds for transferring learning across input sizes.
arXiv:2506. 16704v3 Announce Type: replace Abstract: We study a fundamental question of domain generalization: given a family of domains (i.
arXiv:2606. 11149v1 Announce Type: new Abstract: We study the problem of learning a drifting concept in the presence of Massart noise.
arXiv:2607. 26838v1 Announce Type: new Abstract: In this paper we show that the generalization error of AdaBoost is $\Theta\big(\tfrac{d\ln(n\gamma^{2}/d)}{n\gamma^2}+\tfrac{\ln(1/\delta)}{n}\big)$, where $\gamma$ is the advantage guaranteed by the weak learner, $d$ is the VC-dimension of the class containing the weak hypotheses, $n$ is the sample size, and $\delta$ is the confidence parameter.
arXiv:2511. 02644v2 Announce Type: replace Abstract: We study computable probably approximately correct (CPAC) learning, where learners are required to be computable functions.
arXiv:2605.13684v2 Announce Type: replace Abstract: We study the optimal scale at which real-valued function classes exhibit uniform convergence and learnability. Our main result establishes a scale-...
arXiv:2604. 24749v2 Announce Type: replace Abstract: While the optimal sample complexity of binary classification in terms of the VC dimension is well-established, determining the optimal sample complexity of multiclass classification has remained open.
arXiv:2608. 25326v1 Announce Type: new Abstract: In transductive classification, an adversary fixes a labeled population, one label is hidden uniformly, and the learner sees all remaining labels.
We revisit the problem of learning predictors robust to adversarial examples at test-time. We prove that VC classes are adversarially robustly learnable with sample complexity linear in the VC dimension $d$, providing an exponential improvement over the previous upper bound of Montasser, Hanneke, and Srebro (2019).