Search papers, labs, and topics across Lattice.
School of Electrical and Computer Engineering, Purdue University
2
0
4
The JMDP framework reveals that optimal control can be achieved even in environments with multiple competing actions, fundamentally shifting how we approach decision-making under uncertainty.
Pseudo-calibration can provably salvage conformal prediction's coverage guarantees under distribution shift, offering a way to maintain reliability when your training data doesn't match the real world.