{
  "annotation_id": "1698cc4f-7de6-4aeb-90a6-24ec671c1d9b",
  "date_created": "2026-02-17T05:53:07.569000Z",
  "date_modified": "2026-02-17T05:53:07.569000Z",
  "file_hash": "4a4b64a52169b18121d7b7d9385c25c254b3c3b83e4924da25c6a2001888e715",
  "private": false,
  "record": {
    "abstract": "In large-scale statistical modeling, reducing data size through subsampling is essential for balancing computational efficiency and statistical accuracy. We propose a new method, Principal Component Analysis guided Quantile Sampling (PCA-QS), which projects data onto principal components and applies quantile-based sampling to retain representative and diverse subsets. Compared with uniform random sampling, leverage score sampling, and coreset methods, PCA-QS consistently achieves lower mean squared error and better preservation of key data characteristics, while also being computationally efficient. This approach is adaptable to a variety of data scenarios and shows strong potential for broad applications in statistical computing.",
    "arxiv_id": "2601.06375",
    "authors": [
      "Foo Hui-Mean",
      "Yuan-chin Ivan Chang"
    ],
    "categories": [
      "stat.CO",
      "stat.AP"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Efficient Data Reduction Via PCA-Guided Quantile Based Sampling",
    "url": "https://arxiv.org/abs/2601.06375",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "121cf306-e406-424e-aa4e-8d1212de2c1f",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}