Optimal Estimation of High Dimensional Smooth Additive Function Based on Noisy Observations
Authors: Fan Zhou, Ping Li
ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Numerical simulation results are presented to validate our analysis and show its superior performance of the proposed estimator over the plug-in approach in terms of bias reduction and building confidence intervals. |
| Researcher Affiliation | Industry | Fan Zhou, Ping Li Cognitive Computing Lab Baidu Research 10900 NE 8th St Bellevue WA 98004 USA {fanzhou, liping11}@baidu.com |
| Pseudocode | No | The paper describes the estimator and its components mathematically but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the methodology is openly available. |
| Open Datasets | No | The paper describes generating its own synthetic data for simulations rather than using a publicly available or open dataset. It states: 'The unknown parameters 2 Rd are randomly generated that yield a uniform distribution over [0.2, 0.4]d for different dimension parameter d.' and 'The distribution of " we use is " N(0, σ2Id).' |
| Dataset Splits | No | The paper describes numerical simulations with data generation and independent runs to estimate expectations, variance, and MSE, but it does not specify traditional training, validation, or test dataset splits. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU/CPU models, processor types, memory) used for running its numerical simulations. |
| Software Dependencies | No | The paper mentions the use of 'MATLAB built-in function histfit() and fitdist()' but does not provide specific version numbers for MATLAB or any other software dependencies. |
| Experiment Setup | Yes | We set σ = 1 and n = 104. For the dimension factor, we set d = n and ranges from 0.5 to 0.95 with an incremental size 0.05. The distribution of " we use is " N(0, σ2Id). The additive function we use has a homogeneous H older structure: f( ) := Pd j . We set sample size n = 104 and N = 102 to approximate (7.2). |