(tbd)
specific topics tbd
Part of fair representation learning. Develop a theory of fairness in dimensionality reduction: new definition, new (efficient) algorithm, new theoretical results. Currently focused on PCA.
A new disagreement-based approach to active classification and regression.
Project #1. Clustered State Space Nearly Optimal Latent State Decoding in Block MDPs Accepted to AISTATS 2023 Joint work with Se-Young Yun (KAIST AI) and Yassir Jedra, Alexandre Proutière (KTH EECS).