analiza aiqbench
SPACR introduces a differentiable training framework that aligns model optimization directly with the efficiency goals of Conformal Prediction, eliminating the need for post-hoc adjustments or batch splitting. By jointly optimizing validity and interval tightness within a single pass, the method significantly reduces computational costs while delivering superior coverage-efficiency trade-offs compared to standard approaches. This advancement offers a practical solution for deploying robust uncertainty quantification in production environments where retraining is prohibitive.
SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors
arXiv:2606.10734v1 Announce Type: new Abstract: Conformal Prediction (CP) provides robust uncertainty guarantees for predictive models, but is typically applied post hoc, which misaligns model training with the conformal goal of producing efficient (i.e, narrow) intervals. We propose SPACR (Single-Pass Adaptive Conformal Regressor), a novel method for directly training uncertainty-aware regressors within a differentiable loss. SPACR jointly optimizes efficiency and validity without batch-splitting or a predefined confidence levels during training. As a result, a single SPACR model yields valid prediction intervals at multiple confidence levels during inference, avoiding the costly retraining required by methods like DOICR. Experiments on diverse datasets show that SPACR consistently gives tighter intervals and better coverage-efficiency trade-offs compared to standard CP and DOICR, while significantly reducing computational costs.
Abstract:Conformal Prediction (CP) provides robust uncertainty guarantees for predictive models, but is typically applied post hoc, which misaligns model training with the conformal goal of producing efficient (i.e, narrow) intervals. We propose SPACR (Single-Pass Adaptive Conformal Regressor), a novel method for directly training uncertainty-aware regressors within a differentiable loss. SPACR jointly optimizes efficiency and validity without batch-splitting or a predefined confidence levels during training. As a result, a single SPACR model yields valid prediction intervals at multiple confidence levels during inference, avoiding the costly retraining required by methods like DOICR. Experiments on diverse datasets show that SPACR consistently gives tighter intervals and better coverage-efficiency trade-offs compared to standard CP and DOICR, while significantly reducing computational costs.
Machine Learning (cs.LG); Methodology (stat.ME); Machine Learning (stat.ML)
arXiv:2606.10734 [cs.LG]
(or arXiv:2606.10734v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.10734 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 215 cuvinte
Subiecte conexe
SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors
arXiv · 4 sept. 2026
How Would We Know? Reflections on trying to make AI go well amid deep uncertainty
LessWrong · 5 oct. 2026
Expenditure Horizon: Measuring Optimization Ability, with an Application to NanoGPT
METR · 21 iul. 2026
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · 23 sept. 2026