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.
Tails of Lipschitz Triangular Flows
Authors: Priyank Jaini, Ivan Kobyzev, Yaoliang Yu, Marcus Brubaker
ICML 2020 | Venue PDF | LLM Run Details | Input Tokens: 17,261 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 2,611 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 perform several synthetic and real-world experiments to compliment our theoretical findings. |
| Researcher Affiliation | Collaboration | 1Univesity of Waterloo, Waterloo, Canada 2Vector Institute, Toronto, Canada 3Borealis AI 4York University, Toronto, Canada. |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. There is no specific repository link, explicit code release statement, or mention of code in supplementary materials. |
| Open Datasets | Yes | Lastly, we replicate density estimation experiments on benchmark datasets popularly used to measure performance of flows and autoregressive models. |
| Dataset Splits | Yes | We divided the dataset into training-validation-testing in the ratio 2:1:1. |
| Hardware Specification | Yes | We thank NVIDIA Corporation (the data science grant) for donating two Titan V GPUs that enabled in part the computation in this work. |
| Software Dependencies | No | The paper mentions using "Adam (Kingma & Ba, 2014)" but does not specify version numbers for any software dependencies (e.g., Python, PyTorch, TensorFlow, or Adam itself). |
| Experiment Setup | Yes | We trained the model using Adam (Kingma & Ba, 2014) for 40 epochs with a batch size of 128 and learning rate of 10-3. |