20 results for “distribution shift”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Salim I. Amoukou, Emanuele Albini, Tom Bewley, Saumitra Mishra +1 more
The paper introduces Entropic Projection Alignment (EPA), a unified framework that estimates, explains, and improves model performance under distribution shift by aligning source and target distributi…
This paper presents a double machine learning procedure for estimating the target risk of an arbitrary black-box prediction model under a general loss function.
Gina Wong, Drew Prinster, Suchi Saria, Rama Chellappa +1 more
This paper studies the behavior of mixture-of-experts (MoE) models under distribution shift and proposes an adversarial reweighting method to improve their calibration.
An online monitoring system detects distributional shift in deployed safety classifiers and adapts decision thresholds to recover a target error rate.
Extends conformal predictive systems to non-exchangeable settings by incorporating distributional shifts.
This survey analyzes the field of On-device Learning (ODL) for TinyML by categorizing existing works based on how they address various types of post-deployment distribution changes.
This paper proposes SHIFT, a topology-agnostic approach for communication-aware workload placement and routing optimization in large-scale heterogeneous systems, achieving up to 12.5x throughput impro…
A simple online algorithm is presented for the stacking problem to avoid shifts with a sufficient condition involving stacking area dimension, load/unload points, and maximum items.
Rui Bao, Zheng Gao, Xiaoyu Li, Xiaoyan Feng +2 more
The paper introduces SHIFT, a training-free attack that exploits the vulnerability of diffusion-based watermarking by stochastically deflecting the generative trajectory, achieving high removal rates…
The paper investigates the value of adaptive tuning in log-structured merge trees.
This paper investigates convergence properties of regularized Nyström subsampling for unsupervised domain adaptation under covariate shift.
The paper proposes Fair Fine-tuning (FFt), a method that fine-tunes a model using an Equalized Odds constraint on a complementary distribution, and theoretically proves that this approach significantl…
The paper proposes Fair Fine-tuning (FFt), a method that fine-tunes a model using an Equalized Odds constraint on a complementary distribution, and provides a formal theoretical bound linking this fai…
Yujie Wang, Siwei Chen, Longzan Luo, Xinyi Liu +3 more
The paper proposes DARTS, a distribution-aware active rollout trajectory shaping method that fundamentally accelerates LLM reinforcement learning by actively shaping the long-tail response distributio…
This paper introduces Distributional Random Forests, which replace mean-based CART splitting with criteria that compare full conditional response distributions in candidate children. The authors syste…
This paper studies distribution testing with respect to bounded classes of distinguishers, revealing connections between testable learning, verification of learning algorithms, and testing of structur…