paper-with-me

홈 › Papers

Uniform Deviation Bounds for k-Means Clustering

2017-08-01 · ICML 2017 8 · Olivier Bachem, Mario Lucic, S. Hamed Hassani, Andreas Krause

Uniform deviation bounds limit the difference between a model’s expected loss and its loss on an empirical sample uniformly for all models in a learning problem. In this paper, we provide a novel framework to obtain uniform deviation bounds for loss functions which are unbounded. As a result, we obtain competitive uniform deviation bounds for k-Means clustering under weak assumptions on the underlying distribution. If the fourth moment is bounded, we prove a rate of $O(m^{-1/2})$ compared to the previously known $O(m^{-1/4})$ rate. Furthermore, we show that the rate also depends on the kurtosis – the normalized fourth moment which measures the “tailedness” of a distribution. We also provide improved rates under progressively stronger assumptions, namely, bounded higher moments, subgaussianity and bounded support of the underlying distribution.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Clustering

Methods 이 논문이 사용한 방법론

k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…

Similar Papers 제목 키워드 기반

Uniform Deviation Bounds for Unbounded Loss Functions like k-Means

2017-02-27 · Olivier Bachem, Mario Lucic, S. Hamed Hassani, Andreas Krause

Uniform deviation bounds limit the difference between a model's expected loss and its loss on an empirical sample uniformly for all models in a learning problem. As such, they are a critical component to empirical risk m…

Clustering

Moment-based Uniform Deviation Bounds for $k$-means and Friends

2013-11-08 · Matus Telgarsky, Sanjoy Dasgupta

Suppose $k$ centers are fit to $m$ points by heuristically minimizing the $k$-means cost; what is the corresponding fit over the source distribution? This question is resolved here for distributions with $p\geq 4$ bounde…

Clustering

Moment-based Uniform Deviation Bounds for k-means and Friends

2013-12-01 · NeurIPS 2013 12 · Matus J. Telgarsky, Sanjoy Dasgupta

Suppose $k$ centers are fit to $m$ points by heuristically minimizing the $k$-means cost; what is the corresponding fit over the source distribution? This question is resolved here for distributions with $p\geq 4$ bound…

Clustering

Robust $k$-means Clustering for Distributions with Two Moments

2020-02-06 · Yegor Klochkov, Alexey Kroshnin, Nikita Zhivotovskiy

We consider the robust algorithms for the $k$-means clustering problem where a quantizer is constructed based on $N$ independent observations. Our main results are median of means based non-asymptotic excess distortion b…

ClusteringVocal Bursts Valence Prediction

Sharp uniform convergence bounds through empirical centralization

2020-12-01 · NeurIPS 2020 12 · Cyrus Cousins, Matteo Riondato

We introduce the use of empirical centralization to derive novel practical, probabilistic, sample-dependent bounds to the Supremum Deviation (SD) of empirical means of functions in a family from their expectations. Our b…