Wasserstein Dependency Measure for Representation Learning

Authors: Sherjil Ozair, Corey Lynch, Yoshua Bengio, Aaron van den Oord, Sergey Levine, Pierre Sermanet

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

Reproducibility Variable Result LLM Response
Research Type Experimental In this work, we empirically demonstrate that mutual information-based representation learning approaches do fail to learn complete representations on a number of designed and real-world tasks.
Researcher Affiliation Collaboration Sherjil Ozair Mila, Université de Montréal Corey Lynch Google Brain Yoshua Bengio Mila, Université de Montréal Aäron van den Oord Deepmind Sergey Levine Google Brain Pierre Sermanet Google Brain
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements or links to open-source code for the methodology described.
Open Datasets Yes We used the Omniglot dataset [31] as a base dataset to construct Spatial Multi Omniglot and Stacked Multi Omniglot. ... Shapes3D [27] (Figure 1) is a dataset of images of a single object in a room. ... Celeb A [34] is a dataset consisting of celebrity faces.
Dataset Splits No The paper mentions a fixed training dataset size (50,000 samples) but does not provide specific details for a separate validation split (e.g., percentages or sample counts).
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments (e.g., GPU/CPU models, memory).
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., libraries, frameworks, or specific tools).
Experiment Setup No While the paper discusses the effect of minibatch size, it does not provide concrete hyperparameter values or detailed system-level training configurations needed to reproduce the experiment setup.