Semi-Discrete Normalizing Flows through Differentiable Tessellation

Authors: Ricky T. Q. Chen, Brandon Amos, Maximilian Nickel

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, we show improvements over existing methods across a range of structured data modalities.
Researcher Affiliation Industry Meta AI
Pseudocode No No pseudocode or algorithm blocks were found in the paper.
Open Source Code Yes Open source code is available at https://github.com/facebookresearch/semi-discrete-flow.
Open Datasets Yes We use unprocessed data sets from the UCI database [9].
Dataset Splits Yes We then take 80% as train, 10% as validation, and 10% as the test set.
Hardware Specification No The paper states "All models were trained... on a single GPU," but does not specify the model or any other hardware details.
Software Dependencies No The paper mentions "Adam optimizer [22]" and refers to "torchdiffeq, 2018" from [5] for FFJORD, but does not list specific version numbers for multiple key software components like Python, PyTorch, or CUDA.
Experiment Setup Yes All models were trained using the Adam optimizer [22] with a learning rate of 1e-3, cosine annealing scheduler, and a batch size of 256 for 500 epochs on a single GPU.