|Topic:||Provable Bounds in Machine Learning|
|Affiliation:||Member, Shcool of Mathematics|
|Date:||Wednesday, January 23|
|Time/Room:||6:00pm - 7:30pm/Dilworth Room|
Abstract: Machine learning is a vibrant field with many rich techniques. However, most approaches in the field are heuristic: we cannot prove good bounds on either their performance or their running time, except in quite limited settings. This talk will focus on the project of designing algorithms and estimators whose performance can be analyzed rigorously, and I will give several examples where the key ingredients are ideas from algebra and geometry.