Rob Nowak (UW Madison)
45pm, Mar 30, 2017, Cory 531.
Title and Abstract
Ordinal Embedding
Modeling human perceptions has many applications in cognitive, social, and educational science, as well as in advertising and commerce. I will discuss our ongoing work on ordinal embedding, also known as nonmetric multidimensional scaling, which is the problem of representing items (e.g., images) as points in a lowdimensional Euclidean space given constraints of the form "item i is closer to item j than item k.” In other words, the goal is to find a geometric representation of data that is faithful to comparative similarity judgments. This classic problem is often used to gauge and visualize perceptual similarities. A variety of algorithms exist for learning metric embeddings from comparison data, but the accuracy and performance of these methods were poorly understood. I will present a new theoretical framework that quantifies the accuracy of learned embeddings and indicates how many comparisons suffice as a function of the number of items and the dimension of the embedding. This theory also points to new algorithms that outperform previously proposed methods. I will also describe a few applications of ordinal embedding.
This joint work with Lalit Jain, Kevin Jamieson, and Blake Mason.
Bio
Rob is the McFarlandBascom Professor in Engineering at the University of WisconsinMadison, where his research focuses on signal processing, machine learning, optimization, and statistics. Rob is a professor in Electrical and Computer Engineering, as well as being affiliated with the departments of Computer Sciences, Statistics, and Biomedical Engineering at the University of Wisconsin. He is also a Fellow of the IEEE and the Wisconsin Institute for Discovery, a member of the Wisconsin Optimization Research Consortium and Machine Learning @ Wisconsin, and organizer of the SILO seminar series. Rob is also an Adjoint Professor at the Toyota Technological Institute at Chicago.
