Research map / Learning theory and algorithms / Prediction and decision losses
Beyond Fixed False Discovery Rates: Post-Hoc Conformal Selection With E-Variables
Meiyi Zhu, Osvaldo Simeone
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use post-hoc conformal selection instead of fixed-level CS under a minimum-size constraint | conformal selection · Synthetic and Musk, r_min constraint | selected set size | Improved |
| use post-hoc conformal selection instead of fixed-level CS | conformal selection · Musk | FDP | Hurt |
| use data splitting (Split PH-CS) instead of full-calibration e-variables | PH-CS · Recruitment / Shuttle | utility | Hurt |
| use naive nominal BH level as FDP estimate | PH-CS · Recruitment / Shuttle | FDP/declared ratio | Hurt |
| use PAC bound instead of e-variable average-ratio FDP estimate | PH-CS · Recruitment / Shuttle | FDP estimate tightness | Hurt |
Closest papers by meaning
- Conformalized Multiple Testing after Data-dependent Selection (NeurIPS 2024 · similarity 0.93)
- Online Conformal Selection with Accept-to-Reject Changes (AAAI 2026 · similarity 0.90)
- Multivariate Conformal Selection (ICML 2025 · similarity 0.88)
- Conditional Testing based on Localized Conformal $p$-values (ICLR 2025 · similarity 0.85)
- Calibration without labels in multiple testing (NeurIPS 2026 · similarity 0.85)
- Finite Resources False Discovery Rate Control on Structured Hypothesis Spaces (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
