Research map / Learning theory and algorithms / Matrix and tensor methods
Regression with Label Permutation in Generalized Linear Model
Guanhua Fang, Ping Li
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 |
|---|---|---|---|
| increase number of observations m per individual toward about 10 log2 n | ML estimation for label permutation in GLM (Poisson-type simulations) · simulation, n=256/512 | probability of successful permutation recovery: transition from 0 to 1 near m ≈ 10 log2 n | Improved |
| decrease observation rate q (more missing entries) | ML and two-step estimation with missing observations · simulation | probability of successful permutation recovery | Hurt |
| increase proportion of permuted labels beyond about 20% | two-step estimation · simulation Setting 2 | probability of successful permutation recovery: drops from 1 to 0 around 20% wrong labels | Hurt |
| fit linear model to raw or log-transformed count-type data instead of GLM (ablation) | permutation recovery under model misspecification · simulation Setting 3 | recovery performance | Hurt |
| increase number of responses m for theory of known-B case with Gaussian design (Example 2 and 3) | permutation recovery when B is known · theory, complete/sparse design examples | required m: m ≳ log n suffices vs m=1 impossible | Improved |
Closest papers by meaning
- Optimal Estimator for Unlabeled Linear Regression (ICML 2020 · similarity 0.89)
- Two-Stage Approach to Multivariate Linear Regression with Sparsely Mismatched Data (JMLR 2020 · similarity 0.88)
- Hypothesis Testing for Class-Conditional Noise Using Local Maximum Likelihood (AAAI 2024 · similarity 0.81)
- Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning (ICLR 2024 · similarity 0.81)
- Generalization Analysis for Multi-Label Learning (ICML 2024 · similarity 0.81)
- Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation (ICLR 2024 · 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.
