Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Conformal Frequency Estimation with Sketched Data
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 adaptive (isotonic regression) conformity scores instead of constant scores (ablation) | conformalized sketching · Zipf data, CMS-CU | interval length | Helped |
| conformal bounds versus classical bound | conformalized sketching · Zipf data, CMS-CU | interval length | Helped |
| conformal bounds versus bootstrap bounds on CMS-CU | conformalized sketching · Zipf data, CMS-CU | interval length | Helped |
| conformal bounds versus bootstrap bounds on vanilla CMS | conformalized sketching · Zipf data, vanilla CMS | interval length | No clear effect |
| sketch with CMS-CU instead of vanilla CMS (ablation) | all methods · Zipf data | query precision | Helped |
| conformal versus Bayesian method | conformalized sketching · Zipf data | coverage | Helped |
| increase hash width w | conformal methods · SARS-CoV-2 16-mers | interval length | Helped |
| small hash width w | all methods · SARS-CoV-2 16-mers | interval length | No clear effect |
| conformal adaptive lower bound at alpha 0.5 as point estimate | conformalized sketching · SARS-CoV-2 16-mers | absolute deviation | Helped |
| conformal adaptive intervals on power-law 2-gram data | conformalized sketching · English 2-grams | interval length | Helped |
| Bayesian method with narrow hash widths | Bayesian benchmark · English 2-grams | coverage | Hurt |
Closest papers by meaning
- False Coverage Proportion Control for Conformal Prediction (ICML 2025 · similarity 0.81)
- Online conformal prediction with decaying step sizes (ICML 2024 · similarity 0.81)
- Conformal Prediction with Cellwise Outliers: A Detect-then-Impute Approach (ICML 2025 · similarity 0.81)
- Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means (NeurIPS 2026 · similarity 0.81)
- CBMA: Improving Conformal Prediction through Bayesian Model Averaging (ICLR 2025 · similarity 0.81)
- Conformal Prediction as Bayesian Quadrature (ICML 2025 · similarity 0.81)
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.