Learning spatiotemporal piecewise-geodesic trajectories from longitudinal manifold-valued data

Authors: Stéphanie ALLASSONNIERE, Juliette Chevallier, Stephane Oudard

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on synthetic data validate this choice. The model is then applied to the metastatic renal cancer chemotherapy monitoring: we run estimations on RECIST scores of treated patients and estimate the time they escape from the treatment. Experiments highlight the role of the different parameters on the response to treatment.
Researcher Affiliation Academia Juliette Chevallier CMAP, École polytechnique juliette.chevallier@polytechnique.edu Pr Stéphane Oudard Oncology Department USPC, AP-HP, HEGP Stéphanie Allassonnière CRC, Université Paris Descartes stephanie.allassonniere@parisdescartes.fr
Pseudocode No The paper refers to supplementary material for details about algorithmics, but does not include any pseudocode or algorithm blocks in the main text.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository.
Open Datasets No We now run our estimation algorithm on real data from HEGP. We have performed the estimation over a drove of 176 patients of the HEGP.
Dataset Splits No The paper does not provide specific train/validation/test dataset splits for reproducibility.
Hardware Specification No The paper does not explicitly describe the specific hardware (e.g., GPU, CPU models, or cloud instances) used for running its experiments.
Software Dependencies No The paper mentions the use of 'MONOLIX MOdèles NOn LInéaires à effets mi Xtes' but does not provide a specific version number or other software dependencies with versions.
Experiment Setup Yes Moreover, to put the algorithm on a more realistic situation, the synthetic individual times are non-periodically spaced, individual sizes vary between 12 and 18 and the observed values are noisy (σ = 3). We present here a run with a low residual standard variation in respect to the amplitude of the trajectories and complexity of the dataset: σ = 14.50 versus max(γinit 0 , γfin 0 ) γescap 0 = 452.4. We have run the algorithm several times, with different proposal laws for the sampler (a Symmetric Random Walk Hasting-Metropolis within Gibbs one) and different priors.