PhD student, Georgia Institute of Technology
3 papers at NeurIPS 2025
We benchmark feel-good thompson sampling for contextual bandits with MCMC methods and show that they perform well in the linear setting but do not perform well in neural bandit tasks.
We develop and analyze a scalable algorithm for multi-agent RL by sampling from the mean-field distribution of the agents to overcome the curse of dimensionality.
We show that for nxn Boolean matrices with VC-dimension d, we can do matrix-vector multiplication in O(n^{2-1/d}) time, and provide a number of applications and extensions of this result..
