Introduces replay-based continual learning with sequential invariance alignment to learn domain-invariant representations, outperforming baselines on generalization to unseen domains across six datasets in vision, medicine, manufacturing, and ecology.
The Journal of Machine Learning Research , volume=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8verdicts
UNVERDICTED 8representative citing papers
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
The Sinkhorn treatment effect is a new entropic optimal transport measure of divergence between counterfactual distributions that admits first- and second-order pathwise differentiability, debiased estimators, and asymptotically valid tests for distributional treatment effects.
DKPS-based methods predict new model benchmark scores using cached responses, matching baseline mean absolute error with substantially fewer queries and an offline query selection approach.
SED modifies diffusion models to skip zeros during training and inference, preserving sparsity patterns while claiming computational savings and comparable or better generation quality on benchmarks.
A semi-supervised kernel two-sample test integrates unlabeled covariate data to achieve asymptotic normality under the null, higher power than standard kernel tests, and consistency against fixed and local alternatives.
Predictive Bayesian inference posteriors concentrate onto a forward-model-dependent quantity and produce miscalibrated credible sets unless the predictive model contains the true data-generating process.
MIRA is a new analytic score for conditional distribution accuracy derived from equal probability mass assignment, enabling Bayesian model comparison via direct posterior validation.
citing papers explorer
-
Concentration and Calibration in Predictive Bayesian Inference
Predictive Bayesian inference posteriors concentrate onto a forward-model-dependent quantity and produce miscalibrated credible sets unless the predictive model contains the true data-generating process.