Learning spatiotemporal trajectories from manifold-valued longitudinal data

Authors: Jean-Baptiste SCHIRATTI, Stéphanie ALLASSONNIERE, Olivier Colliot, Stanley DURRLEMAN

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on neuropsychological tests scores and estimates of scenarios of AD progression are given in section 4. The model was applied with Ns = 1, 2 or 3 independent sources. In each experiment, the MCMC SAEM was run five times with different initial parameter values. The experiment which returned the smallest residual variance σ2 was kept. The maximum number of iterations was arbitrarily set to 5000 and the number of burn-in iterations was set to 3000 iterations. The limit of 5000 iterations is enough to observe the convergence of the sequences of parameters estimates. As a result, two and three sources allowed to decrease the residual variance better than one source (σ2 = 0.012 for one source, σ2 = 0.08 for two sources and σ2 = 0.084 for three sources).
Researcher Affiliation Academia 1 ARAMIS Lab, INRIA Paris, Inserm U1127, CNRS UMR 7225, Sorbonne Universit es, UPMC Univ Paris 06 UMR S 1127, Institut du Cerveau et de la Moelle epini ere, ICM, F-75013, Paris, France 2CMAP, Ecole Polytechnique, Palaiseau, France
Pseudocode Yes Algorithm 1 Overview of the MCMC SAEM algorithm for the multivariate logistic curves model.
Open Source Code No The paper does not provide an explicit statement or link for open-source code for the described methodology.
Open Datasets Yes We use the neuropsychological assessment test ADAS-Cog 13 from the ADNI1, ADNIGO or ADNI2 cohorts of the Alzheimer s Disease Neuroimaging Initiative (ADNI) [1]. The ADNI is referenced as [1] The Alzheimer s Disease Neuroimaging Initiative, https://ida.loni.usc.edu/
Dataset Splits No The paper does not explicitly specify the training, validation, or test dataset splits using percentages or sample counts. It mentions using '248 individuals' and 'an average of 6 visits per subjects' but no split information for reproducibility.
Hardware Specification No The paper mentions: "We implemented our algorithm in MATLAB without any particular optimization scheme. The 5000 iterations require approximately one day." This does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions that the algorithm was implemented in "MATLAB" but does not specify a version number for MATLAB or any other software dependencies with version numbers.
Experiment Setup Yes The maximum number of iterations was arbitrarily set to 5000 and the number of burn-in iterations was set to 3000 iterations.