Learning Invariances using the Marginal Likelihood
Authors: Mark van der Wilk, Matthias Bauer, ST John, James Hensman
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 5 Experiments We demonstrate our approach on a series of experiments on variants of the MNIST datasets. While MNIST has been accurately solved by other methods, we intend to show that a model like an RBF GP (Radial Basis Function or squared exponential kernel), for which MNIST is challenging, can be significantly improved by learning the correct invariances. For binary classification tasks, we will use the Pòlya-Gamma approximation for the logistic likelihood, while for multi-class classification, we are currently forced to use the Gaussian likelihood. |
| Researcher Affiliation | Collaboration | Mark van der Wilk PROWLER.io Cambridge, UK mark@prowler.io Matthias Bauer MPI for Intelligent Systems University of Cambridge msb55@cam.ac.uk ST John PROWLER.io Cambridge, UK st@prowler.io James Hensman PROWLER.io Cambridge, UK james@prowler.io |
| Pseudocode | No | The paper describes procedures and mathematical formulations but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions 'Affine transform implementation from github.com/kevinzakka/spatial-transformer-network.' in a footnote, but this is a third-party tool and there is no explicit statement about releasing the authors' own source code for their methodology. |
| Open Datasets | Yes | We demonstrate our approach on a series of experiments on variants of the MNIST datasets. |
| Dataset Splits | No | Crucially, we do not require a validation set, but can use the log marginal likelihood of the training data to monitor performance. |
| Hardware Specification | No | The paper does not provide specific details regarding the hardware used for running the experiments. |
| Software Dependencies | No | The paper mentions the use of Gaussian process models and a Pòlya-Gamma approximation, and references an affine transform implementation, but does not provide specific version numbers for any software dependencies or libraries. |
| Experiment Setup | No | While the paper describes the types of transformations and objectives used in experiments, it does not provide specific hyperparameters such as learning rates, batch sizes, number of epochs, or optimizer settings. |