paper-with-me

홈 › Papers

Linear-Complexity Exponentially-Consistent Tests for Universal Outlying Sequence Detection

2017-01-21 · Yuheng Bu, Shaofeng Zou, Venugopal V. Veeravalli

The problem of universal outlying sequence detection is studied, where the goal is to detect outlying sequences among $M$ sequences of samples. A sequence is considered as outlying if the observations therein are generated by a distribution different from those generating the observations in the majority of the sequences. In the universal setting, we are interested in identifying all the outlying sequences without knowing the underlying generating distributions. In this paper, a class of tests based on distribution clustering is proposed. These tests are shown to be exponentially consistent with linear time complexity in $M$. Numerical results demonstrate that our clustering-based tests achieve similar performance to existing tests, while being considerably more computationally efficient.

📄 PDF Abstract BibTeX arXiv:1701.06084

Code (0)

등록된 구현이 없습니다.

Tasks

Clustering

Similar Papers 제목 키워드 기반

Semiparametric KSD test: unifying score and distance-based approaches for goodness-of-fit testing

2025-12-23 · Zhihan Huang, Ziang Niu arxiv

Goodness-of-fit (GoF) tests are fundamental for assessing model adequacy. Score-based tests are appealing because they require fitting the model only once under the null. However, extending them to powerful nonparametric…

Efficient Spectral Control of Partially Observed Linear Dynamical Systems

2025-05-27 · Anand Brahmbhatt, Gon Buzaglo, Sofiia Druchyna, Elad Hazan

We propose a new method for the problem of controlling linear dynamical systems under partial observation and adversarial disturbances. Our new algorithm, Double Spectral Control (DSC), matches the best known regret guar…

Exponentially Consistent Kernel Two-Sample Tests

2018-02-23 · Shengyu Zhu, Biao Chen, Zhitang Chen

Given two sets of independent samples from unknown distributions $P$ and $Q$, a two-sample test decides whether to reject the null hypothesis that $P=Q$. Recent attention has focused on kernel two-sample tests as the tes…

Change DetectionVocal Bursts Valence Prediction

Algorithmic Foundations of Deep Learning: Complexity-Theoretic Rates and a Characterization of Universal Approximation

2026-06-25 · Anastasis Kratsios, Simone Brugiapaglia, Bum Jun Kim, Gregory Cousins 외 arxiv

Feedforward neural network (NN) expressivity is typically studied by emulating optimal basis-expansion schemes. While powerful, this perspective is incomplete: it primarily captures complexity through regularity, and the…

On the Expressive Power of Transformers for Maxout Networks and Continuous Piecewise Linear Functions

2026-03-03 · Linyan Gu, Lihua Yang, Feng Zhou arxiv

Transformer networks have achieved remarkable empirical success across a wide range of applications, yet their theoretical expressive power remains insufficiently understood. In this paper, we study the expressive capabi…