On Variational Bounds of Mutual Information

Authors: Ben Poole, Sherjil Ozair, Aaron Van Den Oord, Alex Alemi, George Tucker

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

Reproducibility Variable Result LLM Response
Research Type Experimental On high-dimensional, controlled problems, we empirically characterize the bias and variance of the bounds and their gradients and demonstrate the effectiveness of our new bounds for estimation and representation learning.
Researcher Affiliation Collaboration 1Google Brain 2MILA 3Deep Mind. Correspondence to: Ben Poole <pooleb@google.com>.
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks. It describes algorithms textually but not in a formal pseudocode format.
Open Source Code No The paper does not provide any concrete access to source code for the methodology described, nor does it include a specific repository link or an explicit code release statement.
Open Datasets Yes Finally, we highlight the utility of these bounds for disentangled representation learning on the d Sprites datasets (Matthey et al., 2017). [...] d Sprites (Matthey et al., 2017).
Dataset Splits No The paper discusses 'batch size' and 'minibatches' for training but does not explicitly provide specific dataset split information like exact percentages, sample counts for train/validation/test sets, or citations to predefined splits for reproduction.
Hardware Specification No The paper does not provide any specific hardware details (e.g., exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers like Python 3.8, PyTorch 1.9) needed to replicate the experiment.
Experiment Setup Yes The single-sample unnormalized critic estimates of MI exhibit high variance, and are challenging to tune for even these problems. [...] While INCE is a poor estimator of MI with the small training batch size of 64, the interpolated bounds are able to provide less biased estimates than INCE with less variance than INWJ. [...] We use the convolutional encoder architecture from Burgess et al. (2018); Locatello et al. (2018) for p(y|x), and a two hidden layer fully-connected neural network to parameterize the unnormalized variational marginal q(y) used by IJS.