Learning Hierarchical Priors in VAEs

Authors: Alexej Klushyn, Nutan Chen, Richard Kurle, Botond Cseke, Patrick van der Smagt

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To validate our approach, we consider the following experiments. In Sec. 4.1, we demonstrate that our method learns to represent the degree of freedom in the data of a moving pendulum. In Sec. 4.2, we generate human movements based on the learned latent representations of real-world data (CMU Graphics Lab Motion Capture Database). In Sec. 4.3, the marginal log-likelihood on standard datasets such as MNIST, Fashion-MNIST, and OMNIGLOT is evaluated. In Sec. 4.4, we compare our method on the high-dimensional image datasets 3D Faces and 3D Chairs.
Researcher Affiliation Collaboration 1Machine Learning Research Lab, Volkswagen Group, Germany 2Department of Informatics, Technical University of Munich, Germany
Pseudocode Yes Algorithm 1 (REWO) Reconstruction-error-based weighting of the objective function
Open Source Code No The paper does not provide an explicit statement about releasing source code or a link to a code repository.
Open Datasets Yes CMU Graphics Lab Motion Capture Database (http://mocap.cs.cmu.edu), MNIST [18, 17], Fashion-MNIST [29], and OMNIGLOT [16]
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments (e.g., CPU/GPU models, memory).
Software Dependencies No The paper does not specify software dependencies with version numbers (e.g., Python, specific deep learning frameworks like TensorFlow or PyTorch, with their versions).
Experiment Setup Yes In the GECO update scheme (Eq. (5)), β increases/decreases until ˆCt = κ2. ... βt = βt 1 exp ν fβ(βt 1, ˆCt κ2; τ) (ˆCt κ2) ... Initialise β 1 ... ˆCt = (1 α) ˆCba + α ˆCt 1