paper-with-me

홈 › Papers

Non-Convex SGD Learns Halfspaces with Adversarial Label Noise

2020-06-11 · NeurIPS 2020 12 · Ilias Diakonikolas, Vasilis Kontonis, Christos Tzamos, Nikos Zarifis

We study the problem of agnostically learning homogeneous halfspaces in the distribution-specific PAC model. For a broad family of structured distributions, including log-concave distributions, we show that non-convex SGD efficiently converges to a solution with misclassification error $O(\opt)+\eps$, where $\opt$ is the misclassification error of the best-fitting halfspace. In sharp contrast, we show that optimizing any convex surrogate inherently leads to misclassification error of $\omega(\opt)$, even under Gaussian marginals.

📄 PDF Abstract BibTeX arXiv:2006.06742

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Provable Robustness of Adversarial Training for Learning Halfspaces with Noise

2021-04-19 · Difan Zou, Spencer Frei, Quanquan Gu

We analyze the properties of adversarial training for learning adversarially robust halfspaces in the presence of agnostic label noise. Denoting $\mathsf{OPT}_{p,r}$ as the best robust classification error achieved by a …

ClassificationGeneral ClassificationRobust classification

Efficient Testable Learning of General Halfspaces with Adversarial Label Noise

2024-08-30 · Ilias Diakonikolas, Daniel M. Kane, Sihan Liu, Nikos Zarifis

We study the task of testable learning of general -- not necessarily homogeneous -- halfspaces with adversarial label noise with respect to the Gaussian distribution. In the testable learning framework, the goal is to de…

Efficiently Learning Adversarially Robust Halfspaces with Noise

2020-05-15 · ICML 2020 1 · Omar Montasser, Surbhi Goel, Ilias Diakonikolas, Nathan Srebro

We study the problem of learning adversarially robust halfspaces in the distribution-independent setting. In the realizable setting, we provide necessary and sufficient conditions on the adversarial perturbation sets und…

Learning large-margin halfspaces with more malicious noise

2011-12-01 · NeurIPS 2011 12 · Phil Long, Rocco Servedio

We describe a simple algorithm that runs in time poly(n,1/gamma,1/eps) and learns an unknown n-dimensional gamma-margin halfspace to accuracy 1-eps in the presence of malicious noise, when the noise rate is allowed to…

Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach

2023-10-23 · Yinan Li, Chicheng Zhang

We study the problem of computationally and label efficient PAC active learning $d$-dimensional halfspaces with Tsybakov Noise~\citep{tsybakov2004optimal} under structured unlabeled data distributions. Inspired by~\cite{…

Active Learning