Student-t Variational Autoencoder for Robust Density Estimation

Authors: Hiroshi Takahashi, Tomoharu Iwata, Yuki Yamanaka, Masanori Yamada, Satoshi Yagi

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments with various datasets show that training of the Student-t VAE is robust, and the Student-t VAE achieves high density estimation performance.
Researcher Affiliation Industry 1 NTT Software Innovation Center 2 NTT Communication Science Laboratories 3 NTT Secure Platform Laboratories
Pseudocode No The paper describes the methods mathematically but does not include structured pseudocode or an algorithm block.
Open Source Code No The paper does not provide a statement or link indicating that the source code for the proposed methodology is openly available.
Open Datasets Yes The SMTP data is the same as the data used in Section 3, where we used 10% of this dataset for training. We also used 10% of this dataset for validation and the remaining 80% for test. The Aloi data is the Amsterdam library of object images [Geusebroek et al., 2005], and the Thyroid, Cancer and Satellite datasets were obtained from the UCI Machine Learning Repository [Lichman, 2013]. We used the transformations of these datasets by [Goldstein and Uchida, 2016] 3. We used 50% of the dataset for training, 10% for validation, and the remaining 40% for test. The total number of data points and the dimensions of the observation of the five datasets are listed in Table 1.
Dataset Splits Yes We used 10% of this dataset for validation and the remaining 80% for test. ... We used 50% of the dataset for training, 10% for validation, and the remaining 40% for test.
Hardware Specification Yes We used the following setup: CPU was Intel Xeon E5-2640 v4 2.40GHz, the memory size was 1 TB, and GPU was NVIDIA Tesla M40.
Software Dependencies No The paper mentions 'scikit-learn' and 'Adam' but does not provide specific version numbers for these or other software dependencies.
Experiment Setup Yes We used two-layer neural networks (500 hidden units per layer) as the encoder and the decoder, and a hyperbolic tangent as the activation function. We trained the VAE by using Adam [Kingma and Ba, 2014] with mini-batch size of 100. We set the sample size of the reparameterization trick to L = 1. The maximum number of epochs was 500, and we used early-stopping [Goodfellow et al., 2016] based on the validation data. We used a two-dimensional latent variable vector z with the SMTP data, and a 20-dimensional latent variable vector for the other datasets.