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.
Revisiting Spatial Invariance with Low-Rank Local Connectivity
Authors: Gamaleldin Elsayed, Prajit Ramachandran, Jonathon Shlens, Simon Kornblith
ICML 2020 | Venue PDF | LLM Run Details | Input Tokens: 20,194 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 6,700 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 performed classification experiments on MNIST, CIFAR-10, and Celeb A datasets. We trained our models without data augmentation or regularization to focus our investigation on the pure effects of the degree of spatial invariance on generalization. |
| Researcher Affiliation | Industry | 1Google Research, Brain Team. |
| Pseudocode | Yes | Algorithm 1 Low Rank Locally Connected Layer |
| Open Source Code | Yes | Code is available at github.com/google-research/googleresearch/tree/master/low_rank_local_connectivity. |
| Open Datasets | Yes | We performed classification experiments on MNIST, CIFAR-10, and Celeb A datasets. |
| Dataset Splits | Yes | Our division of training, validation and test subsets are shown in Table Supp.1." and "The optimal rank in LRLC is obtained by evaluating models on a separate validation subset. |
| Hardware Specification | Yes | We used Tensor Processing Unit (TPU) accelerators in all our training. |
| Software Dependencies | No | The paper mentions the use of the Adam optimizer and batch normalization but does not provide specific version numbers for any software dependencies like deep learning frameworks (e.g., TensorFlow, PyTorch) or other libraries. |
| Experiment Setup | Yes | In our experiments, we used the Adam optimizer with a maximum learning rate of 0.01 and a minibatch size of 512. We trained our models for 150 epochs starting with a linear warmup period of 10 epochs and used a cosine decay schedule afterwards. |