2 papers
cs.LG2026
Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift
Surbhi Goel, Jonathan Pei, James Wang
Behavior cloning provides strong imitation learning guarantees when training and test environments share the same dynamics. However, in many deployment settings the test environmen…
cs.LG2026
Weight Clipping for Robust Conformal Inference under Unbounded Covariate Shifts
James Wang, Surbhi Goel
Conformal prediction (CP) provides powerful, distribution-free prediction sets, but its guarantees rely on the exchangeability of training and test data, which is often violated in…