paper-with-me

Papers

Nearly Tight Bounds for Robust Proper Learning of Halfspaces with a Margin

2019-08-29 · NeurIPS 2019 12 · Ilias Diakonikolas, Daniel M. Kane, Pasin Manurangsi

We study the problem of {\em properly} learning large margin halfspaces in the agnostic PAC model. In more detail, we study the complexity of properly learning $d$-dimensional halfspaces on the unit ball within misclassification error $\alpha \cdot \mathrm{OPT}_{\gamma} + \epsilon$, where $\mathrm{OPT}_{\gamma}$ is the optimal $\gamma$-margin error rate and $\alpha \geq 1$ is the approximation ratio. We give learning algorithms and computational hardness results for this problem, for all values of the approximation ratio $\alpha \geq 1$, that are nearly-matching for a range of parameters. Specifically, for the natural setting that $\alpha$ is any constant bigger than one, we provide an essentially tight complexity characterization. On the positive side, we give an $\alpha = 1.01$-approximate proper learner that uses $O(1/(\epsilon^2\gamma^2))$ samples (which is optimal) and runs in time $\mathrm{poly}(d/\epsilon) \cdot 2^{\tilde{O}(1/\gamma^2)}$. On the negative side, we show that {\em any} constant factor approximate proper learner has runtime $\mathrm{poly}(d/\epsilon) \cdot 2^{(1/\gamma)^{2-o(1)}}$, assuming the Exponential Time Hypothesis.

📄 PDF Abstract BibTeX arXiv:1908.11335

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Tight Generalization Bounds for Large-Margin Halfspaces

2025-02-19 · Kasper Green Larsen, Natascha Schalburg

We prove the first generalization bound for large-margin halfspaces that is asymptotically tight in the tradeoff between the margin, the fraction of training points with the given margin, the failure probability and the …

Generalization Bounds

Robust and Private Learning of Halfspaces

2020-11-30 · Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thao Nguyen

In this work, we study the trade-off between differential privacy and adversarial robustness under L2-perturbations in the context of learning halfspaces. We prove nearly tight bounds on the sample complexity of robust p…

Adversarial Robustness

A Fine-Grained Understanding of Uniform Convergence for Halfspaces

2026-05-07 · Aryeh Kontorovich, Kasper Green Larsen arxiv

We study the fine-grained uniform convergence behavior of halfspaces beyond worst-case VC bounds. For inhomogeneous halfspaces in $\mathbb{R}^d$ with $d\ge 2$, we show that standard first-order VC bounds are essentially …

VC Dimension and Distribution-Free Sample-Based Testing

2020-12-07 · Eric Blais, Renato Ferreira Pinto Jr., Nathaniel Harms

We consider the problem of determining which classes of functions can be tested more efficiently than they can be learned, in the distribution-free sample-based model that corresponds to the standard PAC learning setting…

PAC learning

Tight Bounds on $\ell_1$ Approximation and Learning of Self-Bounding Functions

2014-04-18 · Vitaly Feldman, Pravesh Kothari, Jan Vondrák

We study the complexity of learning and approximation of self-bounding functions over the uniform distribution on the Boolean hypercube ${0,1}^n$. Informally, a function $f:{0,1}^n \rightarrow \mathbb{R}$ is self-boundin…