微薄的成功:假设检验中不可学习性的理论
Meager Success: A Theory of the Unlearnable for Hypothesis Testing
AI总结:
研究当统计推断的逐点一致性标准无法实现时,提出固定推断问题并确定可实现的最高标准,定义比逐点一致性弱的标准层次,给出不可能定理及其他定理来刻画标准的可实现性。
摘要:
当统计推断的逐点一致性标准(在世界的每个可能状态下都收敛到真理)被证明无法实现时,通常的反应是改变推断目标或加强背景假设。本文追求第三种方法:保持推断问题不变,并确定仍然可实现的最高标准。我定义了一个比逐点一致性弱的标准层次,用拓扑术语表示,要求不是在所有地方而是在“大”的概率测度集上收敛到真理。主要结果是一个不可能定理:对于有限精度测试,当两个假设在它们的并集中稠密时,在每个假设内密集地收敛到真理已经会在一个贫集(“拓扑上几乎所有”)的测度集上导致不一致。条件独立性的无分布检验就是这样一种情况。另外两个定理用纯粹的拓扑术语精确刻画了每个较弱标准何时可实现,补充了Boeken等人(2026年)对逐点一致性的分析。
英文摘要:
When the standard of pointwise consistency for statistical inference -- convergence to the truth in every possible state of the world -- is provably unachievable, the usual responses are to change the inferential target or to strengthen background assumptions. This paper pursues a third: hold the inference problem fixed and identify the highest standard that remains achievable. I define a hierarchy of standards weaker than pointwise consistency, cast in topological terms, requiring convergence to the truth not everywhere but on a ``large'' set of probability measures. The main result is an impossibility theorem: for finite-precision tests, converging to the truth densely within each hypothesis already forces inconsistency on a comeager -- ``topologically almost all'' -- set of measures, whenever the two hypotheses are dense in their union. Distribution-free testing of conditional independence is one such case. Two further theorems characterize, in purely topological terms, exactly when each weaker standard is achievable, complementing Boeken et al.'s (2026) analysis of pointwise consistency.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。