Newest papers

Asymmetric Likelihood-Free Hypothesis Testing

Gunjan Kumar, Yash Pote, Jonathan Scarlett · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29798 · cited by 0 works (OpenAlex) · open-access PDF

Vietnamese

Trong thử nghiệm giả thuyết phân phối không xác suất thấp hơn (LFHT), lấy mẫu từ hai phân phối không xác định $P,Q$ trên $[n]$ với $\mathrm{d_TV}}(P,Q)\geq\varepsilon$, và từ phân phối thứ ba $D\in\{P,Q\}$, mục tiêu là xác định liệu $D=P$ hoặc $D=Q$. Chúng tôi nghiên cứu giả thuyết phân phối không xác suất không đồng bộ, nơi ngân sách mẫu $s_P$ và $s_Q$ cho $P$ và $Q$ có thể khác nhau, và đặc trưng cho ba $(s_P,Q,Q,D) để xác định các yếu tố logarithmic. Chúng tôi thiết lập rằng các ngân sách phân phối không đồng đều có thể cung cấp một sự tiết kiệm đa nguyên tử được biết đến.

Machine translation (Meta M2M100); the English original follows.

Abstract

In likelihood-free hypothesis testing (LFHT), given samples from two unknown distributions $P,Q$ on $[n]$ with $\mathrm{d_{TV}}(P,Q)\geq\varepsilon$, and from a third distribution $D\in\{P,Q\}$, the goal is to identify whether $D=P$ or $D=Q$. We study asymmetric likelihood-free hypothesis testing, where the sample budgets $s_P$ and $s_Q$ for $P$ and $Q$ may differ, and characterize the feasible triples $(s_P,s_Q,s_D)$ up to logarithmic factors. We establish that unequal reference budgets can give a polynomial saving. For instance, for constant separation, $n$ samples from $P$ and $n^{3/4}$ from $Q$ allow testing with $\widetilde O(n^{1/4})$ samples from $D$, whereas both existing baselines---symmetric LFHT and unequal-sample closeness testing---require $Ω(\sqrt n)$ samples from $D$. We further apply our results to non-adaptive distribution 2-clustering, where the sample allocation among $k$ distributions must be fixed before observing any data. We obtain matching upper and lower bounds for this problem up to logarithmic factors in terms of the domain size, number of distributions, smaller cluster size, and separation, both with one cluster distribution known and with both unknown. Comparing with known bounds for adaptive sample allocation gives a worst-case adaptivity gap of $\widetildeΘ(k^{1/4})$.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Mathematics, Closeness, Matching (statistics), Logarithm, Sample (material), Statistical hypothesis testing

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29798, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange