Robust Hypothesis Testing Using Wasserstein Uncertainty Sets

Authors: RUI GAO, Liyan Xie, Yao Xie, Huan Xu

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Real-data example using human activity data demonstrated the excellent performance of the new robust detector. [...] Section 5 demonstrates the excellent performance of our robust detectors using real-data for human activity detection.
Researcher Affiliation Academia Rui Gao School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332 rgao32@gatech.edu Liyan Xie School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332 lxie49@gatech.edu Yao Xie School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332 yao.xie@isye.gatech.edu Huan Xu School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332 huan.xu@isye.gatech.edu
Pseudocode No The paper does not contain any pseudocode or algorithm blocks. It presents mathematical formulations and theoretical derivations.
Open Source Code No The paper does not provide any statements about releasing source code or links to a code repository.
Open Datasets Yes We adopt a dataset released by the Wireless Sensor Data Mining (WISDM) Lab in October 2013. The data in this set were collected with the Actitracker system, which is described in [19, 29, 15].
Dataset Splits No The paper mentions using a dataset for 'human activity detection' and analyzes 'pre-change' and 'post-change' data for sequential observations, but it does not specify explicit training, validation, and test splits with percentages or sample counts.
Hardware Specification No The paper does not provide any specific hardware details such as GPU models, CPU types, or memory specifications used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x).
Experiment Setup Yes We set θ1 = θ2 = θ as the sample sizes are identical, and θ is chosen such that the quantity 1 1/2 infφ Φ(φ; P 1 , P 2 ) in Table 1, or equivalently, the divergence between P 1 and P 2 , is close to zero with high probability if Q1 and Q2 are bootstrapped from the data before change, where P 1 , P 1 is the LFD yielding from (6). [...] For each sequence, we choose the threshold for detection by controlling the type-I error.