cs.LGNov 9, 2026

Generalized Adaptive Boosting and the Geometry of Mistakes

Authors: Marco Bressan, Nataly Brukhim, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen

Organizations: Università degli Studi di Milano · Apple Research · Tel Aviv University · Google Research · 

Abstract

Not all mistakes are alike. For example, in medical diagnosis, false positive and false negative mistakes have a different impact and should not be aggregated. By revisiting the classical theory of boosting through this lens, we introduce the notion of ZZ-learner, which returns weak hypotheses achieving joint false-positive/false-negative guarantees (FP,FN)(\mathrm{FP},\mathrm{FN}) from some set Z⊆[0,1]2Z \subseteq [0,1]^2. This formulation generalizes the standard notion of γγ-weak learning--recovered by taking Z={(z1,z2):z1+z2<1/2−γ}Z=\{(z_1,z_2): z_1+z_2<1/2-γ\}--and allows for more flexible notions of weak learnability that account for the impact of the distribution on the achievable learning guarantees. This raises a natural question: which sets ZZ are boostable? We answer this by giving a complete geometric characterization that unifies, as special cases, both the classical boosting dichotomy and the recent multi-objective extension of Bressan et al. (COLT 2025). We also present an adaptive algorithm for boosting ZZ-learners without relying on the prior knowledge of ZZ, generalizing AdaBoost's ability to handle unknown margin parameters. Finally, we demonstrate that ZZ-learners can achieve confidence amplification. However, the analysis is significantly more involved than in classical boosting and relies on the centerpoint theorem from discrete and computational geometry.

Figures & tables

Explore similar work

Jul 29, 2026

Tight Generalization Bound for AdaBoost

In this paper we show that the generalization error of AdaBoost is Θ(dln⁡(nγ2/d)nγ2+ln⁡(1/δ)n)Θ\big(\tfrac{d\ln(nγ^{2}/d)}{nγ^2}+\tfrac{\ln(1/δ)}{n}\big), where γγ is the advantage guaranteed by the weak learner, dd is the VC-dimension of the class containing the weak hypotheses, nn is the sample size, and δδ is the confidence parameter. The contribution of this paper is the upper bound; the matching lower bound follows from prior work. The upper bound proof follows by combining the known fact that AdaBoost outputs a voting classifier whose voting function has zero empirical γ/2γ/2-margin loss with what is, to the best of our knowledge, a new margin-based generalization bound for voting classifiers.
Aug 13, 2026

Defensive Boosting for Online Probabilistic Forecasting

We study online probabilistic forecasting of binary outcomes chosen by an adaptive adversary. Given an online learning algorithm for a weak hypothesis class HH, we would like to efficiently obtain two incomparable guarantees that existing online boosting techniques provide separately. Online gradient boosting competes in Brier score with the best predictor induced by the span of HH on every sequence, but promises nothing when the span does not contain an accurate predictor. Online weak-to-strong boosting drives classification error to zero under a weak-learning condition, but promises little when that condition fails. We give a simple defensive forecasting algorithm, the Defensive Booster, that obtains both guarantees. On every adaptive sequence, its Brier score is competitive with the best prediction induced by the span of HH at the same rate as online gradient boosting; simultaneously, whenever the realized transcript satisfies the smooth weak-learning condition, its Brier score and randomized classification error satisfy the same rate guarantee as online classification boosting. This is achieved by operationalizing the "dual view" of boosting: When the algorithm's randomized classification error is persistently high, its mistake weights form a smooth reweighting on which every weak hypothesis has low edge, yielding an ex-post hard-core certificate that the weak-learning condition fails. We also develop a strongly adaptive variant, which satisfies both guarantees on every time interval. The Defensive Booster is very efficient: it accesses just one weak-class learner, whereas the prior online boosting methods we compare against maintain large weak-learner ensembles. Experiments on synthetic and real data streams demonstrate its strong predictive performance (sometimes substantially improving over all prior baselines) coupled with orders-of-magnitude faster runtime.
Aug 13, 2026

Bagging Robustly Learns VC Classes with Linear Sample Complexity

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 dd, providing an exponential improvement over the previous upper bound of Montasser, Hanneke, and Srebro (2019). Remarkably, this result is achieved with a simple improper algorithm that combines the classic heuristic bagging (bootstrap aggregation) of Breiman (1996) with robust empirical risk minimization (RERM). Our algorithm computes RERMs on O(d⋆)O(d^\star) independent bootstrap samples and outputs their majority vote, where d⋆d^\star denotes the dual VC dimension. We complement this result with a lower bound showing that this is unavoidable: in general, any learner in this oracle model requires Ω(d⋆)Ω(d^\star) calls to an RERM oracle, even when given arbitrarily many training examples.