证明了在随机性假设下，置信预测方法已达效率极限。
Universality of conformal prediction under the assumption of randomness
- 基于独立同分布假设，分析置信预测的最优效率边界。
- 发现传统置信预测方法已逼近理论最优，改进空间有限。
- 结果更实用，无需不可知常数，适合实际应用者参考。
置信预测在独立同分布数据假设下可提供有效的集合或函数预测。本文探讨是否存在比置信预测更高效且同样有效的预测方法。结果表明，置信预测方法类具有普遍性：在相同有效性前提下，预测效率的提升极为有限。以往研究依赖算法随机性理论，涉及未指定常数；而本文结果更具实用性，并在某些方面被证明为最优。
原文摘要 · Abstract (English)
Conformal predictors provide set or functional predictions that are valid under the assumption of randomness, i.e., under the assumption of independent and identically distributed data. The question asked in this paper is whether there are predictors that are valid in the same sense under the assumption of randomness and that are more efficient than conformal predictors. The answer is that the class of conformal predictors is universal in that only limited gains in predictive efficiency are possible. The previous work in this area has relied on the algorithmic theory of randomness and so involved unspecified constants, whereas this paper's results are much more practical. They are also shown to be optimal in some respects.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。