Event Outlier Detection in Continuous Time

Authors: Siqi Liu, Milos Hauskrecht

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To test the performance of the methods, we conduct experiments on both synthetic data and real-world clinical data and show the effectiveness of the proposed methods.
Researcher Affiliation Collaboration 1Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, USA 2Borealis AI, Vancouver, BC, Canada.
Pseudocode No The paper describes the methods using mathematical formulations and text, but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes Our implementation of all the methods and the experiments is publicly available.1 https://github.com/siqil/CPPOD
Open Datasets Yes In this part, we use real-world clinical data extracted from the MIMIC III dataset (Johnson et al., 2016).
Dataset Splits Yes We choose the number of hidden units in the model from {64, 128, 256, 512, 1024} by maximizing the likelihood on the internal validation set that consists of 20 percent of the training set.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments, such as GPU/CPU models or other system specifications.
Software Dependencies No The paper mentions using a 'continuous-time LSTM' model, but it does not specify any software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes We choose the number of hidden units in the model from {64, 128, 256, 512, 1024} by maximizing the likelihood on the internal validation set that consists of 20 percent of the training set.