Example Memorization in Learning

Machine learning algorithms extract information from their training data. This is by design, but sometimes occurs in surprising and dramatic ways, with models encoding huge amounts of seemingly irrelevant details. In this talk, we will discuss a line of work exploring this phenomenon and how it relates to the capabilities of modern learning techniques, as well as attacks on privacy such as membership inference and data reconstruction. We will present (highly preliminary) theoretical and experimental results.

(This talk is part of the weekly Machine Learning Lunch Meetings (MLLM), held every Tuesday from 12:15 to 1:15 p.m.  Professors from Computer Sciences, Statistics, ECE, the iSchool, and other departments will discuss their latest research in machine learning, covering both theory and applications. This is a great opportunity to network with faculty and fellow researchers, learn about cutting-edge research at our university, and foster new collaborations. For the talk schedule, please visit https://sites.google.com/view/wiscmllm/home. To receive future weekly talk announcements, please subscribe to our UW Google Group at https://groups.google.com/u/1/a/g-groups.wisc.edu/g/mllm.)