2 papers
cs.LG2024
Learning the Sherrington-Kirkpatrick Model Even at Low Temperature
Gautam Chandrasekaran, Adam Klivans
We consider the fundamental problem of learning the parameters of an undirected graphical model or Markov Random Field (MRF) in the setting where the edge weights are chosen at ran…
cs.DS2024
Efficient Discrepancy Testing for Learning with Distribution Shift
Gautam Chandrasekaran, Adam R. Klivans, Vasilis Kontonis +2
A fundamental notion of distance between train and test distributions from the field of domain adaptation is discrepancy distance. While in general hard to compute, here we provide…