Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding

Authors: Akira Nakagawa, Keizo Kato, Taiji Suzuki

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental This section describes three experimental results. First, the results of the toy dataset are examined to validate our theory. Next, the disentanglement analysis for the Celeb A dataset is presented. Finally, an anomaly detection task is evaluated to show the usefulness of data distribution estimation.
Researcher Affiliation Collaboration 1Fujitsu Limited, Kanagawa, Japan 2Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan 3Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan.
Pseudocode No The paper does not contain any sections or figures explicitly labeled 'Pseudocode' or 'Algorithm', nor does it present any structured code-like blocks.
Open Source Code No The paper does not provide an explicit statement about releasing its source code, nor does it include a link to a code repository for the described methodology.
Open Datasets Yes We use four public datasets : KDDCUP99, Thyroid, Arrhythmia, and KDDCUP-Rev. The details of the datasets and network configurations are given in Appendix H. For a fair comparison with previous works, we follow the setting in Zong et al. (2018). Randomly extracted 50% of the data were assigned to the training and the rest to the testing. Then the model is trained using normal data only. Datasets can be downloaded at https://kdd.ics.uci. edu/ and http://odds.cs.stonybrook.edu.
Dataset Splits Yes Randomly extracted 50% of the data were assigned to the training and the rest to the testing.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory, or cloud computing specifications) used to run the experiments.
Software Dependencies No The paper mentions TensorFlow as the implementation framework but does not provide specific version numbers for TensorFlow or any other software dependencies.
Experiment Setup Yes We train 100 epochs using the Adam optimizer with a learning rate of 0.001.