Hierarchical Implicit Models and Likelihood-Free Variational Inference

Authors: Dustin Tran, Rajesh Ranganath, David Blei

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate diverse applications: a large-scale physical simulator for predator-prey populations in ecology; a Bayesian generative adversarial network for discrete data; and a deep implicit model for text generation.
Researcher Affiliation Academia Dustin Tran Columbia University Rajesh Ranganath Princeton University David M. Blei Columbia University
Pseudocode Yes Algorithm 1: Likelihood-free variational inference (LFVI)
Open Source Code No The paper states that the algorithm is available in Edward [53], which is a probabilistic programming language, but does not provide specific open-source code for the methodology implemented in this paper.
Open Datasets Yes Table 1: Classification accuracy of Bayesian GAN and Bayesian neural networks across small to medium-size data sets. Crabs Pima Covertype MNIST.
Dataset Splits No The paper mentions using datasets like MNIST and Lotka-Volterra simulations but does not specify the train/validation/test splits or a methodology for them.
Hardware Specification No The paper does not provide specific hardware details (like GPU/CPU models or types) used for running its experiments.
Software Dependencies No The paper mentions the use of Edward, a probabilistic programming language, but does not specify its version number or any other software dependencies with specific versions.
Experiment Setup Yes We initialize parameters from a standard normal and apply gradient descent with ADAM. g( | θ) is a 2-layer multilayer perception with Re LU activations, batch normalization, and is parameterized by weights and biases θ. We place normal priors, θ N(0, 1).