← Back to all news
arXiv Machine Learning By Cl\'ement L. Canonne, Yash Pote, Jonathan Scarlett, Joy Qiping Yang

Entropy Equivalence Testing

Read the original on arXiv Machine Learning →

arXiv:2605. 23225v2 Announce Type: replace-cross Abstract: We introduce the problem of \emph{entropy equivalence testing} for probability distributions, a relaxation of the well-studied closeness testing problem, where the distribution testing algorithm is now only required to distinguish, given samples from two unknown distributions $p,q$ and a parameter $\varepsilon \in(0,1/2]$, between $p=q$ and $|H(p)-H(q)| \geq \varepsilon$ (where $H$ denotes the Shannon entropy).

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Statistics ML
Oct 9

Tight Bounds for Equivalence Testing with Non-Adaptive Conditional Samples

The paper presents tight bounds for equivalence testing using non‑adaptive conditional samples. It shows that determining whether two unknown distributions are identical or ε‑far in total variation distance requires ∫Θ((log n)/ε²) queries. Consequently, the query complexity for uniformity, identity, and equivalence testing with non‑adaptive conditional samples is ∫Θ(log n).

By Gautam Kamath
More like this →
arXiv Statistics ML
Sep 25

All you need is log

arXiv:2606. 27349v3 Announce Type: replace-cross Abstract: How different are several probability distributions from one another?

By Akshay Balsubramani
More like this →
arXiv Machine Learning
Jul 20

Testing Distributions Against Bounded Distinguishers

arXiv:2607. 15645v1 Announce Type: cross Abstract: Motivated by the challenge of testing distributions over high-dimensional or continuous domains, we study distribution testing with respect to bounded classes of distinguishers.

By Mark Bun, Rathin Desai, Renato Ferreira Pinto Jr
More like this →