Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition
The Conditional Jensen-Shannon Discrepancy (CJSD) is proposed, which proves a covariate-null property, a drift-mass law, a one-sided misspecification-control inequality, a one-sided misspecification-control inequality, and a fixed-measure metrization via an identifiability lemma.
Abstract
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.
Covariate shift often occurs because, in many real applications, the source and the target observations may be generated from different distributions. In this case, the standard metric under the source distribution is not appropriate. This paper considers deep neural network estimators for nonparametric quantile and Huber regression under covariate shift and from dependent observations. We deal with a generalized Bernstein-type inequality that is satisfied by many classical models, including i.i.d. observations, $\phi$-mixing, strong mixing, and $\mathcal{C}$-mixing processes. To perform the covariate shift phenomenon, we propose a sparse-penalized deep neural network (SPDNN) estimator that takes into account the discrepancy between the source and target distributions of the data. When the density ratio (between the source and target distributions of the covariate) is unknown, a two steps pre-training procedure is carried out: the first step is devoted to the construction of a least squares SPDNN estimator of the density ratio; which is used in the second step to perform a pre-training reweighted SPDNN estimator of the regression function. For both the quantile and the Huber regression, non-asymptotic error bounds of the proposed SPDNN estimators are established in the class of H\"older smooth functions. These estimators can adaptively attain (up to a logarithmic factor) the minimax optimal convergence rate from i.i.d. data as well as from several classical time series models.
W. Kengne, Ehud Mossa Ockegna· arXiv.org· 0 citations
Outcomes are regressed on a calibrated probability vector for unobserved class membership. Under a structural conditional mean excluding the score and conditional calibration, the observed-data model reduces to a partially linear regression. The probability vector is a Berkson-type surrogate for membership, so the effect vector $\tau$ is identified without attenuation. In practice the vector is often coarsened to a hard label - an argmax, a confidence threshold - and that label need not retain the Berkson property. For any coarsening the plug-in estimator converges to $\mathcal{A}\tau$, where $\mathcal{A}-I$ is determined by the regression of the discarded part of the score on the retained part. Coarsening therefore leaves $\tau$ undistorted exactly when that regression vanishes, and otherwise distorts some contrasts far more than others. The same operator determines the bias that drives coverage loss. Where that bias is of the order of the standard error, the Wald interval has limiting coverage $\Phi(z-\nu)-\Phi(-z-\nu)$, with $\nu$ their ratio. A fixed bias sends coverage to zero. Operator, standard error, and - through the uncoarsened estimator - the bias are estimable from observed data, so the implied coverage can be approximated before the interval is reported. Simulations show severe coverage loss after argmax coarsening. Three real-data audits exhibit the direction-specific distortion.
Pooling latent subpopulations can obscure relationships and yield misleading regression conclusions, including Simpson's paradox (SP). We propose a detector based on the steady-state dynamics of constant-step stochastic gradient descent (SGD). Unlike likelihood-based mixture tests and confounder-search methods, it requires neither a normal-mixture specification nor observed candidate confounders. Two linear pieces compete under a winner-take-all squared-error loss, and their normalized terminal separation forms the test statistic. Using diffusion approximations, we derive its asymptotic null distribution for general centered scalar covariates and for Gaussian multivariate covariates under symmetric noise. The distribution-dependent null center reduces to the dimension-free constant $4/\pi$ when both covariates and noise are Gaussian. We establish asymptotic size control and consistency against fixed mixture alternatives under regularity conditions. We extend the method to intercept and partial-mixture heterogeneity and study endogeneity, heteroskedasticity, and nonlinear misspecification. Simulations examine calibration, power, and robustness. Finally, a three-stage Detect--Screen--Verify toolkit separates evidence of heterogeneity from its substantive explanation. Across eight public datasets, it recovers four established SP benchmarks and identifies four cases that, to our knowledge, have not been documented previously. The detector requires neither latent-group labels nor a prespecified number of mixture components.
Simulations show that VIMP and MPLOCO agree most closely when the fitted learner is well aligned with the data-generating mechanism, and clarify when intrinsic and extrinsic importance can be interpreted similarly and when they provide complementary information.
Cross-fitted estimators that transport information from the two labeled sources through source-specific density ratios are proposed that establish asymptotically linear inference for TPR and FPR, consistency and pointwise inference for the ROC curve, and asymptotically normal inference for AUC.
Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, idealized settings and is non-estimable from samples. In this paper, we bridge the gap between theory and practical applications. We first show that existing definition of concept shift breaks when the source and target supports mismatch. Leveraging entropic optimal transport, we propose a key notion: $\gamma^{*}\!$-concept shifts, and derive a general error bound unifying covariate and $\gamma^{*}\!$-concept shifts, which applies to broad loss functions, label spaces, and stochastic labeling. We further develop estimators for these shifts with concentration guarantees, and the DataShifts algorithm, which can quantify distribution shifts and estimate the error bound in most applications - a rigorous and general tool for analyzing learning error under distribution shift.
Hongbo Chen, Li Charlie Xia· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
