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 [1].
Estimating informativeness of samples with Smooth Unique Information
Authors: Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
ICLR 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we test the validity of linearized network approximation in terms of estimating the effects of removing an example and show several applications of the proposed information measures. Additional results and details are provided in the supplementary Sec. A. |
| Researcher Affiliation | Collaboration | 1 Amazon Web Services, 2 USC Information Sciences Institute EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The implementation of the proposed method and the code for reproducing the experiments is available at https:// github.com/awslabs/aws-cv-unique-information. |
| Open Datasets | Yes | Kaggle. Dogs vs. Cats, 2013. URL https://www.kaggle.com/c/dogs-vs-cats/ overview. |
| Dataset Splits | Yes | In all datasets used the validation set also has 1000 samples. |
| Hardware Specification | No | The paper does not provide specific hardware details such as exact GPU/CPU models or processor types used for running its experiments. |
| Software Dependencies | No | The paper does not specify software dependencies with version numbers (e.g., Python, libraries, or frameworks with their respective versions) required to replicate the experiment. |
| Experiment Setup | Yes | For the MLP network on MNIST 4 vs 9 we set t = 2000 and η = 0.001; for the Res Net-18 on cats vs dog classification t = 1000 and η = 0.001; and for the Res Net-18 on i Cassava dataset t = 5000 and η = 0.0003. |