arXiv AI
When Can We Trust the Matching Principle? Robust Deployment Geometry Under Finite-Sample and Model Uncertainty
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 11
Conformal Calibration Transfer
Conformal Calibration Transfer addresses the challenge of applying conformal prediction when labeled calibration data is only available in a source space, while predictions are needed in a target space linked via unlabeled paired observations. The proposed Transported Conformal Calibration (TCC) method transports source calibration into the target domain and then corrects residual mismatches using only unlabeled target inputs, with two variants: TCC‑KS, which conservatively adjusts calibration based on a label‑free uncertainty surrogate, and weighted‑TCC, which reweights transported calibration for efficiency when weights are stable. Finite‑sample target‑domain coverage guarantees are provided, and experiments on CIFAR‑100‑C, Tiny‑ImageNet‑C, and SEN12MS demonstrate reliable coverage transfer without labeled target data, along with label‑free diagnostics to signal when correction is required.
arXiv Machine Learning
Oct 8
Certified by Abstention: Distribution-Free Guarantees for Chain-of-Thought Verifiers at Small Calibration Budgets
arXiv:2610.09541v1 Announce Type: cross Abstract: Signals that predict whether a chain-of-thought (CoT) trace is correct are compared by AUC, but deploying one requires a threshold with a guarantee....
arXiv Machine Learning
Sep 24
CS-WCP: Robust Conformal Sets for LLM-Judge Traffic Shifts with Uncertain Group Proportions
CS-WCP introduces confidence‑set weighted conformal prediction to provide robust prediction sets for large‑language‑model judges when deployment traffic shifts the prevalence of task or policy groups. By constructing simultaneous exact intervals for source and target group masses and taking the union over all compatible ratio vectors, CS‑WCP achieves high coverage (mean 0.973) with few failures across 336 constructed traffic shifts, outperforming standard source conformal prediction. The method offers an auditable coverage safeguard under uncertain mixture weights, focusing on conservative tail protection rather than tighter set sizes.
arXiv Computer Vision
Sep 1
Semi-Dense Matching Uncertainty Is Not Just Local Confidence
arXiv:2608.08685v2 Announce Type: replace Abstract: Reliable semi-dense matching is essential for modern geometric vision systems. Designed under a coarse-to-fine paradigm, it achieves an optimal bal...
arXiv Computer Vision
Oct 7
Revar3r: gauge-aware perturbation uncertainty for feed-forward 3d reconstruction
arXiv:2610.07883v1 Announce Type: new Abstract: A correctly reconstructed distant point appears uncertain even when a frozen 3D model processes equivalent inputs because its output frame rotates frac...
arXiv Machine Learning
Aug 11
The Cost of Adaptivity: Matching Lower Bounds Across Learning Problems
arXiv:2608. 08826v1 Announce Type: new Abstract: Adaptive procedures must work without nuisance information an oracle may use, such as a gradient scale or smoothness index, and robust procedures may have to answer queries whose coordinate and inspection time are chosen only after the data are seen.