BLISS Seminar: Ordinal Embedding

Seminar | March 30 | 4-5 p.m. | 531 Cory Hall

 Rob Nowak, UW Madison

 Electrical Engineering and Computer Sciences (EECS)

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 non-metric multidimensional scaling, which is the problem of representing items (e.g., images) as points in a low-dimensional 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 is joint work with Lalit Jain, Kevin Jamieson, and Blake Mason.

 ashwinpm@berkeley.edu