Back
As we begin deploying machine learning models in consequential settings like medical diagnostics or self-driving vehicles, we need ways of knowing when the model may make a consequential error (for example, that the car doesn't hit a human).
I'll be discussing how to generate rigorous, finite-sample confidence intervals for any prediction task, any model, and any dataset, for free. This will be a chalk talk. I will primarily discuss a flexible method called Learn then Test that works for a large class of prediction problems including those with high-dimensional, structured outputs (e.g. instance segmentation, multiclass or hierarchical classification, protein folding, and so on).
Bio I am Anastasios Nikolas Angelopoulos, a rising third-year Ph.D. student at the University of California, Berkeley. I am privileged to be advised by Michael I. Jordan and Jitendra Malik. From 2016 to 2019, I was an electrical engineering student at Stanford University advised by Gordon Wetzstein and Stephen P. Boyd. A copy of my CV is available below.
Research interests I work on theoretical machine learning with applications in vision and healthcare. My goal is to apply modern statistical ideas to increase robustness of black-box models like deep neural networks. I am motivated by medical diagnostics: statistical reliability will become paramount as computer vision and machine learning become ubiquitous in such high-risk settings. My other applied interests include computational imaging and ophthalmology.
Awards I am generously supported by a National Science Foundation Graduate Research Fellowship and a Berkeley Fellowship. At Stanford I was a National Merit Scholar and received the Terman Award, Phi Beta Kappa, Tau Beta Pi, and departmental distinction. In a past life I was a national champion debater and member of the US National Debate Team.
Please let Michael Mühlebach know if you would like to have a 1-1 meeting with Anastasios.
Anastasios Angelopoulos (University of California, Berkeley)