Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression
Authors: Juno Kim, Dimitri Meunier, Arthur Gretton, Taiji Suzuki, Zhu Li
ICLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We provide a convergence analysis of deep feature instrumental variable (DFIV) regression (Xu et al., 2021), a nonparametric approach to IV regression using data-adaptive features learned by deep neural networks in two stages. We prove that the DFIV algorithm achieves the minimax optimal learning rate when the target structural function lies in a Besov space. |
| Researcher Affiliation | Academia | 1Department of Mathematical Informatics, University of Tokyo 2Center for Advanced Intelligence Project, RIKEN 3Gatsby Computational Neuroscience Unit, University College London |
| Pseudocode | No | The paper describes the DFIV algorithm in prose and mathematical equations in Section 2.3 but does not present it in a structured pseudocode or algorithm block. |
| Open Source Code | No | The paper does not contain any explicit statements or links indicating that source code for the described methodology is publicly available. |
| Open Datasets | No | The paper is theoretical and does not describe experiments using specific datasets. It refers to generic 'm i.i.d. samples D1 = {(xi, zi)}m i=1 from (X, Z) for Stage 1, and n i.i.d. samples D2 = {( yi, zi)}n i=1 from (Y, Z) for Stage 2', which are conceptual samples for theoretical analysis rather than specific public datasets. |
| Dataset Splits | No | The paper is theoretical and does not describe experiments using specific datasets, thus there are no mentions of training/test/validation dataset splits. |
| Hardware Specification | No | The paper is theoretical and does not describe the execution of experiments, therefore no hardware specifications are provided. |
| Software Dependencies | No | The paper is theoretical and does not describe the execution of experiments, therefore no specific software dependencies with version numbers are listed. |
| Experiment Setup | No | The paper is theoretical and does not describe the execution of experiments, therefore no details about experimental setup or hyperparameters are provided. |