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].
Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation
Authors: Yogesh Balaji, Rama Chellappa, Soheil Feizi
NeurIPS 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the effectiveness of our formulation in two applications of GANs and domain adaptation. Our approach can train state-of-the-art GAN models on noisy datasets corrupted with outlier distributions. In particular, the proposed optimization method computes weights for training samples reflecting how difficult it is for those samples to be generated in the model. In domain adaptation, our robust OT formulation leads to improved accuracy compared to the standard adversarial adaptation methods. Our code is available at https://github.com/yogeshbalaji/robust OT. |
| Researcher Affiliation | Academia | Yogesh Balaji Department of Computer Science University of Maryland College Park, MD EMAIL Rama Chellappa Electrical and Computer Engineering and Biomedical Engineering Departments Johns Hopkins University Baltimore, MD EMAIL Soheil Feizi Department of Computer Science University of Maryland College Park, MD EMAIL |
| Pseudocode | Yes | A detailed algorithm can be found in Appendix. |
| Open Source Code | Yes | Our code is available at https://github.com/yogeshbalaji/robust OT. |
| Open Datasets | Yes | We artificially add outlier samples to the CIFAR-10 dataset such they occupy γ fraction of the samples. MNIST and uniform noise are used as two choices of outlier distributions. |
| Dataset Splits | No | The paper states 'performance on a validation set can be used for choosing ρ' but does not provide specific details on the dataset splits (e.g., percentages, sample counts, or explicit methodology for splitting). |
| Hardware Specification | No | The paper mentions 'small batch sizes ( 28) were used due to GPU limitations' but does not specify any particular GPU models, CPU types, or detailed hardware specifications used for running experiments. |
| Software Dependencies | No | The paper does not provide specific version numbers for any software dependencies or libraries (e.g., 'Python 3.8, PyTorch 1.9'). |
| Experiment Setup | Yes | We set λ to a large value (typically λ = 1000) to enforce the constraint on χ2-divergence. |