A new research paper explores the sample complexity of robust binary hypothesis testing across three contamination models: Huber, subtractive, and total variation. The study provides explicit formulas for subtractive contamination and demonstrates that sample complexity can be highly unstable with respect to the contamination parameter $\varepsilon$. The paper also shows that sample complexities across the different models are comparable when $\varepsilon$ is rescaled by constant factors. AI
IMPACT This research contributes to the theoretical understanding of hypothesis testing, which can underpin future advancements in AI model evaluation and robustness.
RANK_REASON The cluster contains a research paper published on arXiv detailing theoretical findings in statistics.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
