利用两个判别器将协变量偏移与机制变化分离：CJSD，一种具有精确协变量-概念分解的条件差异
Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition
查看机构详情
- Center for Management of Information Technologies, Kagoshima University（鹿儿岛大学信息技术管理中心）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究针对流系统专家模型复用、生成或弃权决策问题，提出带精确协变量-概念分解的CJSD方法，通过重启e-检测器实现零假生成/复用，性能优于窗口启发式方法。
中文摘要 AI 辅助
维持专家模型池的流系统必须反复决定是否对到达的数据复用现有专家、生成新专家或弃权（不执行）。我们提出一个决策层，使这三种结果具有统计意义。复用和生成被表述为关于条件（机制层面）差异的单侧序贯假设，由无差异区分隔；弃权（不执行）恰好是两个下注e-过程均未积累足够证据的状态。我们证明了可预测判别器序列的可观测代理差异具有有限时间任意时间有效性，且存在无条件单侧转移至总体量，其中每一侧的松弛是单个判别器的超额风险；经验观察到的向下偏差正则性使生成侧恰好具有保守性。通过重启的e-检测器获得了不牺牲保证的新近性：一组在几何间隔重启时间处的无窗口下注上鞅（内存为O(log t)），误差预算在重启实例间分配，这保留了生命周期任意时间有效性；在专家创建顺序上分配预算同样控制了无限多专家的多重性。在合成多概念流、Electricity、Covertype及重复率高的INSECTS基准上，经实例核算的重启组在切换后实现了零假生成和零假复用，且性能匹配或优于已淘汰的窗口启发式方法（INSECTS-重复准确率为0.675），使部署算法与保证算法完全一致。
英文摘要
After the inputs X are known, how much additional information does the label Y carry about which dataset a sample came from? That single quantity -- estimable as the difference of two discriminators' held-out cross-entropies, D_CJS = CE(Z|X) - CE(Z|X,Y) -- is exactly the part of a dataset difference that covariate shift cannot explain. We propose the Conditional Jensen-Shannon Discrepancy (CJSD): with a task indicator Z, the chain rule I(Z;X,Y) = I(Z;X) + I(Z;Y|X) splits total task discrepancy exactly into a covariate axis and a functional axis, both estimable from two ordinary classifiers, with no task-specific predictors, generative models, or bootstrap surrogates. We prove a covariate-null property (the functional axis is exactly zero under pure covariate shift, however severe), a drift-mass law (D_CJS/ln2 equals the mass of the disagreement region for deterministic labels), a one-sided misspecification-control inequality (each direction of estimation error is bounded, unconditionally, by the excess risk of a single discriminator), and a fixed-measure metrization via an identifiability lemma. Empirically, on a ten-measure battery over 202 dataset pairs (synthetic, Electricity, Covertype), only the two conditional-information estimators -- CJSD and a kNN plug-in for the same estimand -- separate concept from covariate shift with AUC 1.0; the case for CJSD is the estimator: under controlled dimensionality scaling the kNN plug-in fails from d=64 while the discriminator route holds to d=256 with a swappable classifier, and it alone yields paired confidence intervals and sequential extensions from the same learned object. The same estimator audits the conditional fidelity of synthetic-data generators that marginal and joint QA metrics pass, detects annotation-guideline changes invisible to input-space monitors, and supports null-calibrated fairness audits.
