Audited Conformal Prediction for Classification under Unknown Distribution Shift
2026-06-16T07:23:54Z•5ac95a493888b16715bf3e236aabe89399a5a74c8b2a0d6b3a39c00f60679c97
FDR controlRicci flowSPD matricesadaptive conformalaudit modelconformal candidate certificationconformal predictionconvex relaxationdistribution shiftgenerative modelinggraph alignmentnon-exchangeable datanonparametric VIoffline model-based optimizationrerankingretrieval-augmented generationreverse telescoping coordinate systemspectral methodsstochastic trace estimationstructured hypothesis testingtensor trainuncertainty quantificationvariational inference
What happened
Collection of ten 2026 arXiv ML/statistics papers covering uncertainty quantification, optimization certification, and structured modeling. Key contributions include: Audited Conformal Prediction (ACP) for improving conditional coverage under unknown distribution shift; Conformal Candidate Certification (CCC) for certifying offline model-based optimization proposals; finite-resources FDR control for structured hypothesis spaces; a new reverse-telescoping coordinate system for SPD matrices enabling efficient computations and generative flows; Structured Nonparametric Variational Inference (SN‑V
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_stat_ml
- Record identifier
- 5ac95a493888b16715bf3e236aabe89399a5a74c8b2a0d6b3a39c00f60679c97
- Enrichment time
- 2026-06-16T07:23:54Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.