Seminars and Events
An Effective Theory of Bias Amplification
Event Details
Location: CR#1135-#1137 Conference Rooms ISI-MDR
Speaker: Arjun Subramonian, Meta Fair (The speaker will present virtually. ISI Conf room will be used as central viewing location).
REMINDER:
Meeting hosts only admit on-line guests that they know to the Zoom meeting. Hence, you’re highly encouraged to use your USC account to sign into Zoom.
If you’re an outside visitor, please inform us at (nlg-seminar-host(at)isi.edu) to make us aware of your attendance so we can admit you. Specify if you will attend remotely or in person at least one business day prior to the event. Provide your: full name, job title and professional affiliation and arrive at least 10 minutes before the seminar begins.
If you do not have access to the 11th Floor for in-person attendance, please check in at the 10th floor main reception desk to register as a visitor and someone will escort you to the conference room location.
Join Zoom Meeting
https://usc.zoom.us/j/91740925433?pwd=yNCHWQaBD37XBVvx621ns58KlNB58d.1
Meeting ID: 917 4092 5433
Passcode: 804448
Machine learning models can capture and amplify biases present in data, leading to disparate test performance across social groups. To better understand, evaluate, and mitigate these biases, a deeper theoretical understanding of how model design choices and data distribution properties contribute to bias is needed. In this talk, I will discuss how we developed a precise analytical theory in the context of ridge regression, both with and without random projections, where the former models feedforward neural networks in a simplified regime. Our theory offers a unified and rigorous explanation of machine learning bias, providing insights into phenomena such as bias amplification and minority-group bias in various feature and parameter regimes.