Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Minimax Estimation of Conditional Moment Models
Authors: Nishanth Dikkala, Greg Lewis, Lester Mackey, Vasilis Syrgkanis
NeurIPS 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conclude with an extensive experimental analysis of the proposed methods. and 9 Experimental Analysis |
| Researcher Affiliation | Collaboration | Nishanth Dikkala MIT EMAIL Greg Lewis Microsoft Research EMAIL Lester Mackey Microsoft Research EMAIL Vasilis Syrgkanis Microsoft Research EMAIL |
| Pseudocode | Yes | Theorem 4. Consider the algorithm where for t = 1, . . . , T: let , ft = Oracle F (z1:n, ut i = 1{ft(zi) > 0}, wt i = |ft(zi)| ht = Oracle H |
| Open Source Code | Yes | Associated code can be found in https://github.com/microsoft/Adversarial GMM. |
| Open Datasets | Yes | MNIST dataset consisting of grayscale images of 28 28 pixels. |
| Dataset Splits | No | The paper does not explicitly state specific training, validation, or test dataset splits (e.g., percentages or sample counts) needed for reproduction. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions software components like 'Elastic Net CV' and 'neural networks' but does not provide specific version numbers for any software dependencies. |
| Experiment Setup | Yes | We consider the following data generating processes: for nx = 1 and nz 1 y = h0(x[0]) + e + δ, δ N(0, .1) x = γ z[0] + (1 γ) e + γ, z N(0, 2 Inz), e N(0, 2), γ N(0, .1) ... We consider several functional forms for h0 including absolute value, sigmoid and sin functions... We consider as classic benchmarks 2SLS with a polynomial features of degree 3 (2SLS) and a regularized version of 2SLS where Elastic Net CV is used in both stages (Reg2SLS). |