Calibration Count Reuse: Validity Does Not Determine Efficiency
stat.ME, cs.CV, cs.LG
Submitted: 2026-09-21
Updated: 2026-09-21
Comments: 33 pages, including appendices
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Uncertainty Sets for Image Classifiers using Conformal Prediction
- EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification
- Conformal prediction after data-dependent model selection
- Fine-Grained Visual Classification of Aircraft
- Empirical Bernstein Bounds and Sample Variance Penalization
- Long-tail learning via logit adjustment
- Classification with Valid and Adaptive Coverage
- Conformal Inference for Open-Set and Imbalanced Classification
- Sigmoid Loss for Language Image Pre-Training
- Trustworthy Few-Shot Transfer of Medical VLMs through Split Conformal Prediction
Related papers
- Doubly robust inference via calibration
- Bayesian Empirical Bayes: Simultaneous Inference from Probabilistic Symmetries
- Optimal Watermark Localization in Mixed-Source Large Language Model Texts
- Flexible Nonparametric Inference for Causal Effects under the Front-Door Model
- A Greedy PDE Router for Blending Neural Operators and Classical Methods
- Policy Learning with Weak Signals