Adversarial Symmetric Variational Autoencoder

Authors: Yuchen Pu, Weiyao Wang, Ricardo Henao, Liqun Chen, Zhe Gan, Chunyuan Li, Lawrence Carin

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental An extensive set of experiments is performed, in which we demonstrate state-of-the-art data reconstruction and generation on several image benchmark datasets.
Researcher Affiliation Academia Department of Electrical and Computer Engineering, Duke University {yp42, ww109, r.henao, lc267, zg27,cl319, lcarin}@duke.edu
Pseudocode No The paper describes algorithms and formulations mathematically but does not include any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any statements or links indicating that open-source code for the described methodology is available.
Open Datasets Yes We evaluate our model on three datasets: MNIST, CIFAR-10 and Image Net.
Dataset Splits No Early stopping is employed based on average reconstruction loss of x and z on validation sets. The paper mentions using validation sets but does not specify the split percentages, sample counts, or the exact methodology for creating these splits.
Hardware Specification Yes while our model only requires less than 2 days (4 hours per epoch) for training and 0.01 seconds/image for generating on a single TITAN X GPU.
Software Dependencies No The paper mentions optimizers like Adam and initialization methods like Xavier, but does not provide specific version numbers for any software dependencies or libraries used.
Experiment Setup Yes All parameters were initialized with Xavier [36], and optimized via Adam [37] with learning rate 0.0001. We do not perform any dataset-specific tuning or regularization other than dropout [38]. Early stopping is employed based on average reconstruction loss of x and z on validation sets.