Langevin Autoencoders for Learning Deep Latent Variable Models

Authors: Shohei Taniguchi, Yusuke Iwasawa, Wataru Kumagai, Yutaka Matsuo

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

Reproducibility Variable Result LLM Response
Research Type Experimental Using multiple synthetic datasets, we first validate that ALD can properly obtain samples from target posteriors. We also evaluate the LAE on the image generation task, and show that our LAE can outperform existing methods based on variational inference, such as the variational autoencoder, and other MCMC-based methods in terms of the test likelihood. In our experiment, we first test our ALD algorithm on toy examples to investigate its behavior, then we show the results of its application to the training of deep generative models for image datasets.
Researcher Affiliation Academia Shohei Taniguchi The University of Tokyo taniguchi@weblab.t.u-tokyo.ac.jp Yusuke Iwasawa The University of Tokyo iwasawa@weblab.t.u-tokyo.ac.jp Wataru Kumagai The University of Tokyo kumagai@weblab.t.u-tokyo.ac.jp Yutaka Matsuo The University of Tokyo matsuo@weblab.t.u-tokyo.ac.jp
Pseudocode Yes Algorithm 1 Amortized Langevin dynamics; Algorithm 2 Langevin Autoencoders
Open Source Code Yes Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes] See the appendix.
Open Datasets Yes We perform numerical experiments of the image generation task using the MNIST, SVHN, CIFAR-10, and Celeb A datasets.
Dataset Splits No The paper mentions using a "training set" and a "test set" for evaluation, but it does not specify details for a separate validation set or explicit dataset splits (e.g., percentages for train/validation/test) in the provided text.
Hardware Specification Yes Computational resources of AI Bridging Cloud Infrastructure (ABCI) provided by National Institute of Advanced Industrial Science and Technology (AIST) were used for the experiments.
Software Dependencies No The paper states that training details are in the appendix, but the provided text does not include specific software versions (e.g., library names with version numbers) required for replication.
Experiment Setup Yes We set the number of ALD iterations of the LAE to 2, i.e, T = 2 in Algorithm 2. We set σ = 0.05 in the experiment. Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] See the appendix.