Learning in Implicit Generative Models

Authors: Shakir Mohamed, Balaji Lakshminarayanan

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Here, we develop our understanding of GANs with the aim of forming a rich view of this growing area of machine learning to build connections to the diverse set of statistical thinking on this topic, of which much can be gained by a mutual exchange of ideas. We frame GANs within the wider landscape of algorithms for learning in implicit generative models models that only specify a stochastic procedure with which to generate data and relate these ideas to modelling problems in related fields, such as econometrics and approximate Bayesian computation. We develop likelihood-free inference methods and highlight hypothesis testing as a principle for learning in implicit generative models, using which we are able to derive the objective function used by GANs, and many other related objectives.
Researcher Affiliation Industry Shakir Mohamed and Balaji Lakshminarayanan Deep Mind, London {shakir,balajiln}@google.com
Pseudocode No The paper describes various statistical and mathematical formulations, but it does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating that source code for the methodology described is publicly available.
Open Datasets No The paper is a theoretical discussion of implicit generative models and does not describe specific experiments or use any particular datasets that would be made publicly available.
Dataset Splits No The paper is theoretical and does not detail experimental procedures, thus it does not provide information on training, validation, or test dataset splits.
Hardware Specification No The paper is theoretical and does not describe any experiments that would require specific hardware specifications.
Software Dependencies No The paper is theoretical and does not specify any software dependencies or their version numbers, as it does not detail any implementation or experimental setup.
Experiment Setup No The paper is theoretical and focuses on conceptual and mathematical developments, without providing details on specific experimental setups or hyperparameters.