Research & Publications
Research Overview
My research is in machine learning theory, with a focus on learning theory for adaptive and modern machine learning systems.
- Adaptive environments. I am mainly interested in learning dynamics in games and reinforcement learning. I have previously worked on questions about online learning algorithm design and equilibrium.
- Deep learning theory. I study theoretical questions arising from modern machine learning systems. So far, I have been interested in understanding phenomenon and limitations of modern machine learning systems. This leads me to work with model expressivity, neural networks and diffusion models.
- Related areas. I have also worked on sampling, statistical estimation, privacy, and classical learning theory.
Across these topics, I tend to gravitate toward clean theoretical questions with an extremal or optimization flavor: lower bounds, sharp thresholds, minimax rates, optimality guarantees, expressivity, and learning dynamics.
You can also find my publications on my Google Scholar profile.
If you are interested in collaborating, feel free to reach out at viverson@uwaterloo.ca.
Research Directions & Selected Works
Learning in Adaptive Environments
Deep Learning Theory
Sampling & Statistical Estimation
Classical Learning Theory
Other Projects
Talks
I am deeply grateful to my mentors, collaborators, and friends who have profoundly shaped my path as a researcher. I extend particular gratitude to Xiaoheng Wang for introducing me to mathematical research; to Stephen Vavasis and Gautam Kamath for being among the first to mentor me and involve me in machine learning theory research; and to Argyris Mouzakis for his invaluable mentorship and many helpful discussions. I am also indebted to Shai Ben-David, Aukosh Jagannath, and Jeffrey Negrea for inspiring my interest in this field.