Long-term Goal. Making AI more responsible: accessible, sustainable, and righteous.

Current Focus. Various facets of effcient machine learning.

In particular, I try to answer these questions.

  • Given a fixed resource for training and inference, what is the best machine intelligence we can get?
  • How can we effectively utilize the data-level redundancy for efficient training?
  • How can we replace the noise, inherent in ML, with a compute-efficient option?

Papers. See the group webpage.