Research map / Learning theory and algorithms / Sample complexity
Unlinked Monotone Regression
Fadoua Balabdaoui, Charles R. Doss, Cécile Durot
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 proposed minimum contrast estimator instead of deconvolution estimator | unlinked monotone regression · step2, Laplace (n=100) | MSE: 2.84 -> 0.33 | Improved |
| use proposed minimum contrast estimator instead of deconvolution estimator | unlinked monotone regression · step3, Laplace (n=1000) | MSE: 3.34 -> 0.15 | Improved |
| use proposed minimum contrast estimator instead of deconvolution estimator | unlinked monotone regression · const, Gauss (n=1000) | MSE: 0.70 -> 0.03 | Improved |
| use proposed minimum contrast estimator instead of deconvolution estimator | unlinked monotone regression · lin, Laplace (n=100) | MSE: 0.27 -> 0.31 | Hurt |
| use proposed minimum contrast estimator instead of deconvolution estimator | unlinked monotone regression · lin, Gauss (n=1000) | MSE: 0.18 -> 0.29 | Hurt |
| use proposed estimator instead of deconvolution estimator | unlinked monotone regression · power, Gauss (n=1000) | MSE: 0.25 -> 0.25 | No clear effect |
| switch noise from Laplace to Gaussian for proposed estimator | UL BDD · const (n=100) | MSE: 0.18 -> 0.10 | Improved |
| switch noise from Laplace to Gaussian for proposed estimator | UL BDD · lin (n=100) | MSE: 0.31 -> 0.48 | Hurt |
| increase sample size from 100 to 1000 | UL BDD · step2, Laplace | MSE: 0.33 -> 0.12 | Improved |
| use matched-pair information (linked isotonic oracle) instead of unlinked data | UL BDD · step2, Laplace (n=100) | MSE: 0.33 -> 0.09 | Improved |
| use Gaussian-mixture oracle error distribution instead of fitted Laplace | UL BDD · CEX food expenditure vs income | MSE | Mixed |
Closest papers by meaning
- Permuted and Unlinked Monotone Regression in R^d: an approach based on mixture modeling and optimal transport (JMLR 2024 · similarity 0.88)
- Deconvolution in unlinked linear models (JMLR 2026 · similarity 0.85)
- Uncoupled Regression from Pairwise Comparison Data (NeurIPS 2019 · similarity 0.83)
- TIC-TAC: A Framework For Improved Covariance Estimation In Deep Heteroscedastic Regression (ICML 2024 · similarity 0.80)
- Adjust Pearson's $r$ to Measure Arbitrary Monotone Dependence (NeurIPS 2024 · similarity 0.80)
- When Additive Noise Meets Unobserved Mediators: Bivariate Denoising Diffusion for Causal Discovery (NeurIPS 2025 · similarity 0.80)
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.
