This paper characterizes the fundamental limits of mean testing under arbitrary truncation, where a portion of the probability mass is hidden. The research identifies a detectability floor created by truncation bias and proposes a second-order test with near-optimal sample complexity. Additionally, it reveals a method to escape this bias barrier under a directional median regularity assumption, improving the bias to linear order and recovering classical statistical rates. AI
IMPACT Provides theoretical underpinnings for statistical methods that could be applied in machine learning contexts.
RANK_REASON This is a research paper published on arXiv detailing theoretical statistical findings.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
