PulseAugur
EN
LIVE 04:03:34

New MNAR-k-means method improves clustering for missing data

By PulseAugur Editorial · [4 sources] ·

Researchers have developed a new k-means clustering method, MNAR-$k$-means, designed to handle datasets with missing values that are not missing at random (MNAR). This method specifically addresses scenarios where data is more likely to be missing in values with smaller absolute magnitudes. The proposed technique constrains imputation values and has been mathematically interpreted to ensure statistical consistency of estimated cluster centers. An alternative minimization algorithm is used to optimize the loss function, and simulations demonstrate its effectiveness in improving clustering results and reducing bias. AI

IMPACT This research offers a novel approach to clustering incomplete datasets, potentially improving the accuracy of analyses in fields where missing data is common.

RANK_REASON The cluster contains an arXiv preprint detailing a new machine learning method.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

New MNAR-k-means method improves clustering for missing data

COVERAGE [4]

  1. arXiv cs.LG TIER_1 English(EN) · Xin Guan ·

    MNAR-$k$-means: A $k$-means Clustering for Data Missing Not at Random with Magnitude-Decaying Probability

    arXiv:2606.31253v1 Announce Type: cross Abstract: The classical $k$-means clustering, based on distances computed from all data features, cannot be directly applied to incomplete data with missing values. A natural extension of $k$-means to missing data is to involve only the obs…

  2. arXiv stat.ML TIER_1 English(EN) · Xin Guan ·

    Statistical Properties of $k$-means Clustering for Data Missing Completely at Random

    arXiv:2607.01945v1 Announce Type: new Abstract: The classical $k$-means clustering cannot be directly used to incomplete data, and existing $k$-means-based clustering for missing data primarily focus on improving the practical accuracy of clustering, whereas most of them lack the…

  3. arXiv stat.ML TIER_1 English(EN) · Xin Guan ·

    Statistical Properties of $k$-means Clustering for Data Missing Completely at Random

    The classical $k$-means clustering cannot be directly used to incomplete data, and existing $k$-means-based clustering for missing data primarily focus on improving the practical accuracy of clustering, whereas most of them lack theoretical guarantees in the asymptotic sense. In …

  4. arXiv stat.ML TIER_1 English(EN) · Xin Guan ·

    MNAR-$k$-means: A $k$-means Clustering for Data Missing Not at Random with Magnitude-Decaying Probability

    The classical $k$-means clustering, based on distances computed from all data features, cannot be directly applied to incomplete data with missing values. A natural extension of $k$-means to missing data is to involve only the observed positions in clustering, which is equivalent…

RELATED ENTITIES

RELATED TOPICS