Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
On Exact Computation with an Infinitely Wide Neural Net
Authors: Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Russ R. Salakhutdinov, Ruosong Wang
NeurIPS 2019 | Venue PDF | LLM Run Details | Input Tokens: 16,442 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,926 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate the performances of CNNs and their corresponding CNTKs on the CIFAR-10 dataset. The implementation details are in Section A. We also compare the performances between CNTKs and their corresponding random features. Due to space limit, we defer these results on random features to Section B. Results. We test two types of architectures, vanilla CNN and CNN with global average pooling (GAP), as described in Sections 4 and H. We also test CNTKs with only 2,000 training data to see whether their performances are consistent with CNTKs and CNNs using the full training set. The results are summarized in Table 1. |
| Researcher Affiliation | Academia | Princeton University and Institute for Advanced Study. Email: EMAIL Institute for Advanced Study. Email: EMAIL Princeton University. Email: EMAIL Princeton University. Email: EMAIL k Carnegie Mellon University. Email:EMAIL Carnegie Mellon University. Email: EMAIL |
| Pseudocode | No | The paper describes algorithmic steps but does not present them in a structured pseudocode or algorithm block. |
| Open Source Code | No | The paper does not provide an explicit statement about open-sourcing the code or a direct link to a code repository for the described methodology. |
| Open Datasets | Yes | We evaluate the performances of CNNs and their corresponding CNTKs on the CIFAR-10 dataset. |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for training, validation, and test sets. It mentions using 'the full CIFAR-10 dataset' and '2,000 training data' for some experiments, but does not detail how these sets are divided for training, validation, and testing. |
| Hardware Specification | No | The paper states 'We thank Amazon Web Services for providing compute time for the experiments in this paper.' but does not specify exact GPU/CPU models, processor types, or memory amounts used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library names with version numbers, needed to replicate the experiment. |
| Experiment Setup | No | The paper describes the architectures (vanilla CNN, CNN with global average pooling) and depth (e.g., 11-layer, 21-layer) but does not provide specific hyperparameter values like learning rate, batch size, number of epochs, or optimizer settings for the experimental setup. |