4 papers · 1 filter
Iterative Chow Filtering for Learning with Distribution Shift
Gautam Chandrasekaran, Georgios Gkrinias, Adam R. Klivans +2
Recent work due to Goel et al. gave the first efficient algorithms for learning with distribution shift in the challenging PQ framework. In this setting, a learner receives labeled…
A Fully Polynomial-Time Algorithm for Robustly Learning Halfspaces over the Hypercube
Gautam Chandrasekaran, Adam R. Klivans, Konstantinos Stavropoulos +1
We give the first fully polynomial-time algorithm for learning halfspaces with respect to the uniform distribution on the hypercube in the presence of contamination, where an adver…
Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees
Gautam Chandrasekaran, Adam R. Klivans, Lin Lin Lee +1
We give the first provably efficient algorithms for learning neural networks with distribution shift. We work in the Testable Learning with Distribution Shift framework (TDS learni…
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…