Online Algorithm for Unsupervised Sequential Selection with Contextual Information

Authors: Arun Verma, Manjesh Kumar Hanawal, Csaba Szepesvari, Venkatesh Saligrama

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on synthetic and real datasets validate our algorithm. We evaluate the performance of USS-PD on different problem instances derived from synthetic and real datasets.
Researcher Affiliation Collaboration Arun Verma Department of IEOR IIT Bombay, India v.arun@iitb.ac.in; Manjesh K. Hanawal Department of IEOR IIT Bombay, India mhanawal@iitb.ac.in; Csaba Szepesvári Deep Mind/University of Alberta Alberta, Canada szepi@google.com; Venkatesh Saligrama Departmetn of ECE Boston University, USA srv@bu.edu
Pseudocode Yes Algorithm 1 Learning on contextual USS instance (Q, c); USS-PD Algorithm for Contextual USS using Pairwise Disagreement
Open Source Code No The paper does not provide an explicit statement about releasing source code or a link to a code repository for the methodology described.
Open Datasets Yes We applied our algorithm on PIMA Indian Diabetes (Kaggle, 2016) dataset. Heart Disease dataset (Detrano, 1998; Dheeru and Karra Taniskidou, 2017)
Dataset Splits No The paper mentions using a synthetic dataset of 5000 samples and splitting features, but it does not provide specific train/validation/test dataset splits (percentages or counts) for any of the datasets used.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used to run the experiments.
Software Dependencies No The paper mentions training logistic classifiers and implementing settings, implying software use, but does not specify any software libraries or dependencies with their version numbers.
Experiment Setup No The paper mentions varying regularization parameters and costs for creating problem instances, but it does not provide specific hyperparameters (e.g., learning rate, batch size, number of epochs) or system-level training settings for the USS-PD algorithm itself.