Research map / Learning theory and algorithms / Kernels and regression theory
Minimax Estimation of Conditional Moment Models
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 the Nystrom-approximated RKHS minimax estimator | Conditional moment estimation with few treatments · Small-treatment simulation (n=300, n_z=1, n_x=1, γ=.6) | MSE | Helped |
| Use the RFIV reduction with random forest regression and decision-tree classification oracles | Conditional moment estimation · Moderate-instrument-and-treatment simulation (n=2000, n_z=10, n_x=10, γ=.6) | MSE | Helped |
| Use AGMM or KLayerTrained neural-network estimators | Conditional moment estimation · Moderate-instrument-and-treatment simulation (n=2000, n_z=10, n_x=10, γ=.6) | MSE | Helped |
| Use the sparse linear minimax estimator | High-dimensional sparse linear conditional moment model · High-dimensional simulation (n=400, n_z=n_x:=p, γ=.6) | MSE | Helped |
| Use AGMM or KLayerTrained neural-network estimators | Image-based conditional moment estimation · High-dimensional DGPs using MNIST images | MSE | Helped |
| Add a second-moment penalty on test functions (ablation) | Minimax criterion for conditional moment estimation · General conditional moment models | Projected MSE rate | Helped |
Closest papers by meaning
- Estimation Beyond Data Reweighting: Kernel Method of Moments (ICML 2023 · similarity 0.87)
- Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate Shift (ICLR 2025 · similarity 0.87)
- Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions (ICML 2022 · similarity 0.87)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.86)
- Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression (ICLR 2025 · similarity 0.85)
- Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions (ICML 2024 · 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.