Exchangeable Generative Models with Flow Scans
Authors: Christopher Bender, Kevin O'Connor, Yang Li, Juan Garcia, Junier Oliva, Manzil Zaheer10053-10060
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this work, we develop a new approach to generative density estimation for exchangeable, non-i.i.d. data. ... We achieve new state-of-the-art performance on point cloud and image set modeling. ... In this section, we compare the performance of Flow Scan to that of BRUNO and NS in a variety of exchangeable point cloud and image modeling tasks. |
| Researcher Affiliation | Collaboration | Christopher M. Bender, 1 Kevin O Connor,*2 Yang Li,1 Juan Jose Garcia,1 Junier Oliva,1 Manzil Zaheer3 1Department of Computer Science, UNC Chapel Hill 2Department of Statistics and Operations Research, UNC Chapel Hill 3Google Research |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Further implementation details (including code and Appendices) can be found at https://github.com/lupalab/flowscan. |
| Open Datasets | Yes | We consider object classes from the Model Net dataset (Wu et al. 2015)... Each set consists of 50 points sampled uniformly at random from active pixels of a single MNIST (Le Cun et al. 1998) image with uniform noise added to ensure nondegeneracy. |
| Dataset Splits | No | The paper mentions using a 'held out test set' but does not provide specific details on the train, validation, and test splits (e.g., percentages, sample counts, or explicit splitting methodology). |
| Hardware Specification | No | The paper does not explicitly describe any specific hardware (e.g., GPU/CPU models, memory specifications) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific version numbers for any software dependencies or libraries used. |
| Experiment Setup | No | The paper describes the model architecture and training goals but does not provide specific details about hyperparameters (e.g., learning rate, batch size, epochs) or other fine-grained experimental setup settings. |