{
  "annotation_id": "4c343a12-4f5b-4800-9d4d-b16459c8b6b2",
  "date_created": "2026-02-17T05:53:16.126000Z",
  "date_modified": "2026-02-17T05:53:16.126000Z",
  "file_hash": "01279189fb18c3e9c6f939399761ebbbc20724efbe79a7a2ef00dc70e493182b",
  "private": false,
  "record": {
    "abstract": "We consider the classical problem of discrete distribution estimation using i.i.d. samples in a novel scenario where additional side information is available on the distribution. In large alphabet datasets such as text corpora, such side information arises naturally through word semantics/similarities that can be inferred by closeness of vector word embeddings, for instance. We consider two specific models for side information--a local model where the unknown distribution is in the neighborhood of a known distribution, and a partial ordering model where the alphabet is partitioned into known higher and lower probability sets. In both models, we theoretically characterize the improvement in a suitable squared-error risk because of the available side information. Simulations over natural language and synthetic data illustrate these gains.",
    "arxiv_id": "2601.08535",
    "authors": [
      "Haricharan Balasundaram",
      "Andrew Thangaraj"
    ],
    "categories": [
      "cs.IT",
      "math.IT"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Distribution Estimation with Side Information",
    "url": "https://arxiv.org/abs/2601.08535",
    "version": "v2"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "4cfd28cc-c3dc-4312-b1d1-173235ee8053",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}