Decomposing feature-level variation with Covariate Gaussian Process Latent Variable Models
Authors: Kaspar Märtens, Kieran Campbell, Christopher Yau
ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the utility of our model on simulated examples and applications in disease progression modelling from high-dimensional gene expression data in the presence of additional phenotypes. In each setting we show how the c-GPLVM can extract low-dimensional structures from high-dimensional data sets whilst allowing a breakdown of feature-level variability that is not present in other commonly used dimensionality reduction approaches. (Abstract) and 5. Experiments (Section title) |
| Researcher Affiliation | Academia | 1Department of Statistics, University of Oxford, UK 2Department of Statistics, University of British Columbia, Canada 3BC Cancer Agency, Canada 4UBC Data Science Institute, Canada 5The Alan Turing Institute, UK 6Institute of Cancer and Genomic Sciences, University of Birmingham, UK. |
| Pseudocode | No | The paper describes the methods textually and mathematically but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our implementation of c-GPLVM is available in https: //github.com/kasparmartens/c-GPLVM. |
| Open Datasets | Yes | We now consider a real world data set consisting of N = 770 breast cancers from The Cancer Genome Atlas cohort (Weinstein et al., 2013). |
| Dataset Splits | No | The paper mentions 'For 5 patients at a time, we artificially censor their survival time by half a year' and 'on repeated sampling from the posterior', but it does not provide specific training, validation, or test dataset split percentages or counts needed for reproduction. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU or GPU models, memory specifications, or cloud instance types) used for running the experiments. |
| Software Dependencies | No | The paper mentions its implementation is available on GitHub but does not specify any software dependencies (libraries, frameworks, or languages) with version numbers. |
| Experiment Setup | Yes | Variational inducing point based inference (Titsias, 2009; Damianou et al., 2016) can be adopted for c-GPLVM in a straightforward way. (Section 3.3) and For this purpose, we specify σ2 z, σ2 x, σ2 xz Γ(1, 1). (Section 3.2.2) and we choose q(xi) = T N [ai,bi](µi, σ2 i ) where µi, σ2 i are variational parameters. (Section 3.4) |