paper-with-me

홈 › Papers

Testing Halfspaces over Rotation-Invariant Distributions

2018-10-31 · Nathaniel Harms

We present an algorithm for testing halfspaces over arbitrary, unknown rotation-invariant distributions. Using $\tilde O(\sqrt{n}\epsilon^{-7})$ random examples of an unknown function $f$, the algorithm determines with high probability whether $f$ is of the form $f(x) = sign(\sum_i w_ix_i-t)$ or is $\epsilon$-far from all such functions. This sample size is significantly smaller than the well-known requirement of $\Omega(n)$ samples for learning halfspaces, and known lower bounds imply that our sample size is optimal (in its dependence on $n$) up to logarithmic factors. The algorithm is distribution-free in the sense that it requires no knowledge of the distribution aside from the promise of rotation invariance. To prove the correctness of this algorithm we present a theorem relating the distance between a function and a halfspace to the distance between their centers of mass, that applies to arbitrary distributions.

📄 PDF Abstract BibTeX arXiv:1811.00139

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Downsampling for Testing and Learning in Product Distributions

2020-07-15 · Nathaniel Harms, Yuichi Yoshida

We study distribution-free property testing and learning problems where the unknown probability distribution is a product distribution over $\mathbb{R}^d$. For many important classes of functions, such as intersections o…

Data-driven Cloud Clustering via a Rotationally Invariant Autoencoder

2021-03-08 · Takuya Kurihana, Elisabeth Moyer, Rebecca Willett, Davis Gilton 외

Advanced satellite-born remote sensing instruments produce high-resolution multi-spectral data for much of the globe at a daily cadence. These datasets open up the possibility of improved understanding of cloud dynamics …

Clustering

Testing Distributions Against Bounded Distinguishers

2026-07-17 · Mark Bun, Rathin Desai, Renato Ferreira Pinto arxiv

Motivated by the challenge of testing distributions over high-dimensional or continuous domains, we study distribution testing with respect to bounded classes of distinguishers. A representative task is to use samples fr…

Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution

2018-11-23 · Yang You, Yujing Lou, Qi Liu, Yu-Wing Tai 외

Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown. In this paper, we propose a brand new point-set learning framework PRIN, namely, P…

3D Feature MatchingData Augmentation

Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins

2020-10-01 · Spencer Frei, Yuan Cao, Quanquan Gu

We analyze the properties of gradient descent on convex surrogates for the zero-one loss for the agnostic learning of linear halfspaces. If $\mathsf{OPT}$ is the best classification error achieved by a halfspace, by appe…

General Classification