I’m a computer science researcher with 5+ years experience using algorithms, machine learning, and applied math to solve complex problems in a variety of application areas. Recent projects include: predicting the effectiveness of anti-cancer drugs, analyzing recommender systems, and developing a mathematical model of contact tracing. I’m currently a PhD candidate (graduating May 2024) at Cornell University, where I’m advised by Jon Kleinberg.

Before the PhD, I was a software engineer at Google Research and earned bachelor’s and master’s degrees in computer science from Stanford University, where I worked with Greg Valiant. A life-long athlete, I played competitive ultimate frisbee for 10 years, during which I competed in multiple national- and world-championships and learned a ton about teamwork, dedication, and resilience. Since moving to Ithaca, NY, I get my competitive fix racing gravel bikes through the stunning forests of the Finger Lakes region.

Recent Highlights

• Summer 2023: Interned in the computational oncology division at Memorial Sloan Kettering Cancer Center, where I developed an ML model to predict drug response in pre-clinical studies. [Paper] [Code]
• Presented our work on algorithmic problems in contact tracing at the Cornell AI Seminar, Duke Probability Seminar, and in the multi-institution Global Pervasive Computational Epidemiology Seminar. [Talk]

Papers

Predicting drug response via transfer learning
Michela Meister, Christopher Tosh and Wesley Tansey
(Submitted as workshop paper to Machine Learning for Health) [Paper] [Code]

Containing the spread of a contagion on a tree
Michela Meister and Jon Kleinberg
(In submission) [Paper] [Talk]

Optimizing the order of actions in a model of contact tracing
Michela Meister and Jon Kleinberg
PNAS Nexus [Paper]

Learning with Comparison Feedback: Online Estimation of Sample Statistics
Michela Meister and Sloan Nietert
Algorithmic Learning Theory (ALT) 2021 [Paper]

Tight Dimensionality Reduction for Sketching Low Degree Polynomial Kernels
Michela Meister, Tamás Sarlós, and David P. Woodruff
Advances in Neural Information Processing Systems (NeurIPS) 2019 [Paper]

A Data Prism: Semi-verified learning in the small-alpha regime
Michela Meister and Gregory Valiant
Conference on Learning Theory (COLT) 2018 [Paper]

Other Writing

Digital Security and Reproductive Rights: Lessons for Feminist Cyberlaw
Michela Meister and Karen Levy
To appear in Feminist Cyberlaw

Fellowships

• NDSEG Fellowship [2019-2022]

Teaching

I served as a graduate teaching assistant for the following courses.

• Cornell: Networks
• Stanford: Optimization and Algorithmic Paradigms; Probability for Computer Scientists; Mathematical Foundations of Computing; Mathematical Methods for Robotics, Vision, and Graphics