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].
Kernel Neural Optimal Transport
Authors: Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev
ICLR 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We test NOT with kernel costs on the unpaired image-to-image translation task.In this section, we test our algorithm on an unpaired image-to-image translation task. |
| Researcher Affiliation | Academia | Alexander Korotin Skolkovo Institute of Science and Technology Artificial Intelligence Research Institute Moscow, Russia EMAIL Daniil Selikhanovych Skolkovo Institute of Science and Technology Moscow, Russia EMAIL Evgeny Burnaev Skolkovo Institute of Science and Technology Artificial Intelligence Research Institute Moscow, Russia EMAIL |
| Pseudocode | No | The paper references 'NOT s training procedure (Korotin et al., 2023, Algorithm 1)' but does not include a pseudocode block or algorithm within this paper itself. |
| Open Source Code | Yes | The code is written in Py Torch framework and is available at https://github.com/iamalexkorotin/Kernel Neural Optimal Transport |
| Open Datasets | Yes | Image datasets. We test the following datasets as P, Q: aligned anime faces1, celebrity faces (Liu et al., 2015), shoes (Yu & Grauman, 2014), Amazon handbags, churches from LSUN dataset (Yu et al., 2015), outdoor images from the MIT places database (Zhou et al., 2014), describable textures (Cimpoi et al., 2014). |
| Dataset Splits | No | We pick 90% of each dataset for unpaired training. The rest 10% are considered as the test set. The paper explicitly mentions train and test splits but no dedicated validation split. |
| Hardware Specification | Yes | NOT with kernel costs for 128 128 images converges in 3-4 days on a 4 Tesla V100 GPUs (16 GB). |
| Software Dependencies | No | The paper mentions 'Py Torch framework' and 'Adam optimizer' but does not specify their version numbers or any other software dependencies with specific versions. |
| Experiment Setup | Yes | The learning rate is lr = 1 10 4. We use the Multi Step LR scheduler which decreases lr by 2 after [15k, 25k, 40k, 55k, 70k] (iterations of fω). The batch size is |X| = 64, |Zx| = 4. The number of inner iterations is k T = 10. |