Distribution Estimation with Side Information
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917206076424192 |
|---|---|
| author | Balasundaram, Haricharan Thangaraj, Andrew |
| author_facet | Balasundaram, Haricharan Thangaraj, Andrew |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08535 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Distribution Estimation with Side Information Balasundaram, Haricharan Thangaraj, Andrew Information Theory 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. |
| title | Distribution Estimation with Side Information |
| topic | Information Theory |
| url | https://arxiv.org/abs/2601.08535 |