Sparse Polynomial Learning and Graph Sketching

Authors: Murat Kocaoglu, Karthikeyan Shanmugam, Alexandros G Dimakis, Adam Klivans

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also provide experimental results on a real world dataset. We test our algorithms on a real dataset and show that the algorithm is able to scale well on sparse hypergraphs created out of Yahoo! messenger dataset by filtering through time and location stamps.
Researcher Affiliation Academia 1Department of Electrical and Computer Engineering, 2Department of Computer Science The University of Texas at Austin, USA mkocaoglu@utexas.edu, karthiksh@utexas.edu dimakis@austin.utexas.edu, klivans@cs.utexas.edu
Pseudocode Yes Algorithm 1: Learn Bool
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes We run our algorithm on the Yahoo! Messenger User Communication Pattern Dataset [17]. [17] Yahoo, Yahoo! webscope dataset ydata-ymessenger-user-communication-pattern-v1 0, http: //research.yahoo.com/Academic Relations.
Dataset Splits No The paper describes parameters for data collection and interval selection (e.g., δt, δx, m) but does not provide specific train/validation/test dataset split percentages or counts, or refer to predefined splits.
Hardware Specification Yes We performed simulations using MATLAB on an Intel(R) Xeon(R) quad-core 3.6 GHz machine with 16 GB RAM and 10M cache.
Software Dependencies No The paper mentions using 'MATLAB' but does not specify its version number or any other software dependencies with specific version details.
Experiment Setup Yes For each time interval, the error probability is calculated by averaging the number of errors among 100 different trials. Table 1: Simulation parameters for Fig. 1b