Anastasios Angelopoulos
Ph.D. candidate in Electrical Engineering and Computer Science
at the University of California, Berkeley
Student of Michael I. Jordan
and of Jitendra Malik
Research interests
I am broadly interested in the use of black-box machine learning models for decision-making and statistical inference, as well as cross-disciplinary research in imaging, medicine, and biology. I'm especially excited about bridging modern AI systems with statistics to ensure their effective and responsible use. See here for more!Recent News
October, 2024 I gave my dissertation talk! And once I file my thesis, I'll start as a PostDoc with Ion Stoica working on trustworthy AI systems and evaluations.
September, 2024 Check out Functional protein mining with conformal guarantees, our method for reliable protein search, in collaboration with Ron Boger, Seyone Chithrananda, and Jennifer Doudna.
June, 2024 This summer I will be a Student Researcher at Google DeepMind, working on new evaluation methodologies for safer, stronger LLMs.
May, 2024 Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictions appeared at ICRA'24.
November, 2023 Prediction-Powered Inference was published in Science.
