Systems | Information | Learning | Optimization
 

Block CUR Decompostion: Matrix Approximation Using Groups of Columns and Inferring Relationships in High-dimensional Generalized Linear Autoregressive Processes

Video: https://vimeo.com/163595515 Urvashi Oswal – Block CUR Decomposition: Matrix Approximation using Groups of Columns A common problem in large-scale data analysis is approximating a matrix using a combination of specifically sampled rows and columns. Unfortunately, in many real-world environments, the ability to sample specific individual rows or columns of the …

Information Aggregation through Price and Learning Social Networks with Online Convex Programming and Parametric Dynamics

We describe a novel approach to online convex programming in dynamic settings. Many existing online learning methods are characterized via regret bounds that quantify the gap between the performance of the online algorithm relative to a comparator. In previous work, this comparator was either considered static over time, or admitted …