covariate-shift

Tag

Cards List
#covariate-shift

Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition

arXiv cs.LG · 2026-08-21 Cached

The paper proposes CJSD, a method using two discriminators to exactly separate covariate shift from mechanism change in datasets, with theoretical guarantees and empirical results.

0 favorites 0 likes
#covariate-shift

Certify or Refuse: A Cross-Model Map for Selective Risk Control with Coverage Floors under Covariate Shift

arXiv cs.CL · 2026-08-12 Cached

This paper introduces a cross-model map for certifying selective predictors that must meet both an automation floor and a risk ceiling under covariate shift, deriving feasibility frontiers and two-resource sample-complexity trade-offs.

0 favorites 0 likes
#covariate-shift

CalTwin: Towards Calibrated, Shift-Robust Medical World Models via Fisher-Information Regularisation

arXiv cs.LG · 2026-07-30 Cached

CalTwin introduces a Fisher-Information-based regularization to improve robustness to covariate shift and confidence misalignment in medical world models, achieving modest improvements on the PhysioNet 2019 Sepsis Challenge dataset.

0 favorites 0 likes
#covariate-shift

ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies

arXiv cs.LG · 2026-06-30 Cached

ReGuide introduces a self-improving framework for diffusion policies that uses test-time guidance to generate corrective rollouts, then fine-tunes the policy on this data, achieving 1.3–7.7× success improvement on Robomimic tasks.

0 favorites 0 likes
#covariate-shift

Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift

arXiv cs.LG · 2026-05-22 Cached

This paper introduces the Expectation Consistency Loss (ECL), a theoretically grounded loss function for calibrating classifier confidence under covariate shift, derived from a necessary and sufficient condition called the Expectation Consistency Condition.

0 favorites 0 likes
#covariate-shift

TILT: Target-induced loss tilting under covariate shift

arXiv cs.LG · 2026-05-15 Cached

TILT introduces a novel objective for unsupervised domain adaptation under covariate shift that penalizes an auxiliary component on unlabeled target data, implicitly achieving self-localized importance weighting with bounded estimands. Theoretical guarantees and experiments on shifted CIFAR-100 show improved target performance over baselines.

0 favorites 0 likes
#covariate-shift

Revisiting DAgger in the Era of LLM-Agents

Hugging Face Daily Papers · 2026-05-13 Cached

This paper revisits Dataset Aggregation (DAgger) for training long-horizon LLM agents, demonstrating that turn-level teacher-student policy interpolation mitigates covariate shift and outperforms existing methods on software engineering benchmarks like SWE-bench Verified.

0 favorites 0 likes
← Back to home

Submit Feedback