# Tight Bounds for Differentially Private Anonymized Histograms

arXiv: https://arxiv.org/abs/2111.03257 · HTML: https://mlsanity.com/paper/2111.03257/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2021.

## Built on by (most cited first, 2 of 2)

- [Private Isotonic Regression](https://mlsanity.com/paper/2210.15175/) (2022)
- [Anonymized Histograms in Intermediate Privacy Models](https://mlsanity.com/paper/2210.15178/) (2022)

## Abstract (arXiv)

In this note, we consider the problem of differentially privately (DP) computing an anonymized histogram, which is defined as the multiset of counts of the input dataset (without bucket labels). In the low-privacy regime ε ≥ 1, we give an ε-DP algorithm with an expected ℓ1-error bound of O(√n / eε). In the high-privacy regime ε < 1, we give an Omega(√n log(1/ε) / ε) lower bound on the expected ℓ1 error. In both cases, our bounds asymptotically match the previously known lower/upper bounds due to [Suresh, NeurIPS 2019].