Multimodal Generative Models for Scalable Weakly-Supervised Learning

Authors: Mike Wu, Noah Goodman

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

Reproducibility Variable Result LLM Response
Research Type Experimental We report experiments to measure the quality of the MVAE, comparing with previous models. We train on MNIST [14], binarized MNIST [13], Multi MNIST [6, 20], Fashion MNIST [30], and Celeb A [15]. Several of these datasets have complex modalities character sequences, RGB images requiring large inference networks with RNNs and CNNs. We show that the MVAE is able to support heavy encoders with thousands of parameters, matching state-of-the-art performance.
Researcher Affiliation Academia Mike Wu Department of Computer Science Stanford University Stanford, CA 94025 wumike@stanford.edu Noah Goodman Departments of Computer Science and Psychology Stanford University Stanford, CA 94025 ngoodman@stanford.edu
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes We train on MNIST [14], binarized MNIST [13], Multi MNIST [6, 20], Fashion MNIST [30], and Celeb A [15].
Dataset Splits No The paper mentions training, but does not explicitly provide training/validation/test dataset splits needed to reproduce the experiment, such as specific percentages or sample counts for each split.
Hardware Specification No The paper does not explicitly describe the hardware used to run its experiments.
Software Dependencies No The paper mentions using Adam and RNN architectures from [2] but does not provide specific version numbers for software components or libraries.
Experiment Setup Yes We use Adam with a 10 4 learning rate, a batch size of 50, λi = 1 for i = 1, ..., N, β annealing for 20 out of 100 epochs.