Research map / Learning theory and algorithms / Sample complexity
Time-uniform confidence bands for the CDF under nonstationarity
Paul Mineiro, Steven R Howard
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 DDRM instead of Emp. Bern for the pointwise confidence sequence | Importance-weighted CDF bands · Beta(6, 3), W_t ~ Exp(1) | maximum bound width: 0.10 -> 0.09 | Improved |
| Use DDRM instead of Emp. Bern for the pointwise confidence sequence | Importance-weighted CDF bands · Beta(6, 3), W_t ~ Exp(1) | time (sec) for 1000 equally spaced points: 1.0 -> 24.8 | Hurt |
| Use DDRM instead of Emp. Bern for the pointwise confidence sequence | Importance-weighted CDF bands · Beta(6, 3), W_t ~ Pareto(3/2) | maximum bound width: 0.125 -> 0.052 | Improved |
| Use DDRM instead of Emp. Bern for the pointwise confidence sequence | Importance-weighted CDF bands · Beta(6, 3), W_t ~ Pareto(3/2) | time (sec) for 1000 equally spaced points: 2.4 -> 59.4 | Hurt |
| Use Emp. Bern instead of DDRM for the pointwise confidence sequence | Importance-weighted CDF bands · Importance weights with infinite variance | convergence | Hurt |
| Use value-space discretization and pointwise confidence sequences to construct bands | Nonstationary averaged conditional CDF · Continuous Polya urn | coverage | Improved |
| Use importance-weighted confidence bands for the target distribution | Importance-weighted CDF bands · Nonstationary importance-weighted continuous Polya urn | coverage | Improved |
Closest papers by meaning
- Asymptotic Anytime-Valid Inference for U-statistics (NeurIPS 2026 · similarity 0.86)
- Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy (ICML 2024 · similarity 0.85)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.85)
- Gambling-Based Confidence Sequences for Bounded Random Vectors (ICML 2024 · similarity 0.84)
- PAC-Bayes-Chernoff bounds for unbounded losses (NeurIPS 2024 · similarity 0.84)
- Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means (NeurIPS 2026 · similarity 0.84)
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.
