Title: Auction Dynamics for Semi-Supervised Data Classification

Date: 02/16/2018

Time: 4:10 PM - 5:00 PM

Place: B117 Wells Hall

We reinterpret the semi-supervised data classification problem using an auction dynamics framework (inspired by real life auctions) in which elements of the data set make bids to the class of their choice. This leads to a novel forward and reverse auction method for data classification that readily incorporates volume/class-size constraints into an accurate and efficient algorithm requiring remarkably little training/labeled data. We prove that the algorithm is unconditionally stable, and state its average and worst case time complexity.