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..
Differential Equation Scaling Limits of Shaped and Unshaped Neural Networks
Authors: Mufan Bill Li, Mihai Nica
TMLR 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Figure 1: Empirical distribution of the transformed correlation rt = log(ℓ2(1 − ρℓ)) for an unshaped ReLU MLP, SDE sample density computed via kernel density estimation. Simulated with n = d = 150, ρ0 = 0.3, r0 = log(0.7), SDE step size 10−2, and 213 samples. |
| Researcher Affiliation | Academia | Mufan (Bill) Li EMAIL Princeton University Mihai Nica EMAIL University of Guelph and Vector Institute |
| Pseudocode | No | The paper describes mathematical formulations and proofs but does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statement about the release of source code, nor does it include links to a code repository. |
| Open Datasets | No | The paper does not mention the use of any external, publicly available datasets. The data for Figure 1 appears to be generated through simulation rather than loaded from a specific dataset. |
| Dataset Splits | No | The paper does not utilize external datasets that would require explicit training/test/validation splits. The presented results are based on mathematical derivations and a simulation without such data partitioning. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used to perform the simulations or computations. |
| Software Dependencies | No | The paper mentions 'Sym Py (Meurer et al., 2017)' for Taylor expansion in the proof of Theorem 4.1, but it does not specify a version number for SymPy or any other software dependencies crucial for replicating the experiments. |
| Experiment Setup | Yes | The simulation shown in Figure 1 specifies concrete parameters: 'Simulated with n = d = 150, ρ0 = 0.3, r0 = log(0.7), SDE step size 10−2, and 213 samples.' |