TY - ELEC
AU - Lizhong Zheng
PY - 2018
TI - Local Geometric Analysis and Applications to Learning Algorithms.
LA - eng
M3 - Moving Image
AB - Local geometric analysis is a method to define a coordinate system in a small neighborhood in the space of distributions and the functional space over a given alphabet. It is a powerful technique since the notions of distance, projection, and inner product defined this way are useful in the optimization problems involving distributions, such as regressions. It has been used in many places in the literature such as correlation analysis, correspondence analysis. In this talk, we will go through some of the basic setups and properties, and discuss a specific problem we called ``universal feature selectionÃ¢ , which has close connections to some of the popular learning algorithms such as matrix completion and deep-learning. We will use this problem to motivate definitions of new information metrics for partial information and the relevance to specific queries.
N2 - Local geometric analysis is a method to define a coordinate system in a small neighborhood in the space of distributions and the functional space over a given alphabet. It is a powerful technique since the notions of distance, projection, and inner product defined this way are useful in the optimization problems involving distributions, such as regressions. It has been used in many places in the literature such as correlation analysis, correspondence analysis. In this talk, we will go through some of the basic setups and properties, and discuss a specific problem we called ``universal feature selectionÃ¢ , which has close connections to some of the popular learning algorithms such as matrix completion and deep-learning. We will use this problem to motivate definitions of new information metrics for partial information and the relevance to specific queries.
UR - https://open.library.ubc.ca/collections/48630/items/1.0378515
ER - End of Reference