Date: March 22, 2018
Location: 126 Clements Hall
Colloquium: 3:45 pm – 4:45 pm
Coffee: 3:30 pm – 3:45 pm
Below is the information on our upcoming colloquium given by Dr. Jack Xin
If you would like to meet with Dr. Jack Xin please sign up using the wiki page:
https://wiki.smu.edu/display/MathSeminarWiki/Jack+Xin%2C+Department+of+Mathematics%2C+UC+Irvine
“Non-convex Relaxation Methods in Data Science”
Dr. Jack Xin
Department of Mathematics
UC Irvine
Constraints with discrete characters appear broadly in data science problems, such as sparsity in compressed sensing and low bit precision weights in deep learning. Even though it is possible to impose hard constraints, their continuous non-convex relaxations can be more effective, and readily integrated with various descent methods in unconstrained settings. We show examples in sparse signal recovery by L1 norm based non-convex penalties, and image classification of quantized deep neural networks.