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..
Generalization in multitask deep neural classifiers: a statistical physics approach
Authors: Anthony Ndirango, Tyler Lee
NeurIPS 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We discuss the validity of our theoretical results in comparison to a comprehensive suite of numerical experiments. |
| Researcher Affiliation | Industry | Tyler Lee Intel AI Lab EMAIL Anthony Ndirango Intel AI Lab EMAIL |
| Pseudocode | No | The paper describes mathematical derivations and processes but does not include any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | Code supporting this paper is available upon request |
| Open Datasets | No | The paper describes a 'student-teacher setup' where data is generated by a teacher network, and does not mention or provide access information for a publicly available dataset. |
| Dataset Splits | No | The paper mentions 'validation error' in Figure 1 caption, implying a validation set was used, but does not provide specific percentages or counts for training, validation, or test dataset splits. |
| Hardware Specification | No | The paper acknowledges 'the compute infrastructure that made the empirical portions of this work possible' but does not provide specific hardware details like CPU/GPU models or types of accelerators. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers used for the experiments. |
| Experiment Setup | Yes | 1/ = 10 3 is the learning rate |