Data-Adaptive Tradeoffs among Multiple Risks in Distribution-Free Prediction

arXiv:2403.19605v1 Announce Type: cross
Abstract: Decision-making pipelines are generally characterized by tradeoffs among various risk functions. It is often desirable to manage such tradeoffs in a data-adaptive manner. As we demonstrate, if this is done naively, state-of-the art uncertainty quantification methods can lead to significant violations of putative risk guarantees.
To address this issue, we develop methods that permit valid control of risk when threshold and tradeoff parameters are chosen adaptively. Our methodology supports monotone and nearly-monotone risks, but otherwise …

abstract art arxiv cs.lg data decision distribution free functions making multiple pipelines prediction quantification risk risks state stat.me type uncertainty