Search papers, labs, and topics across Lattice.
2
0
5
Ditch repeated Riccati equation solves: DeepONets learn a fast, generalizable LQR solution operator, slashing computation time while maintaining provable stability guarantees.
Shapley-based feature attribution for multi-output models *must* decompose component-wise across outputs to satisfy standard fairness axioms, revealing a fundamental constraint on joint-output explanations.
