Search papers, labs, and topics across Lattice.
Affiliation:
2
0
2
Maximizing $L_p$-norms over zonotopes is W[1]-hard for all fixed rational $p \in (1, \infty)$, revealing deep computational challenges in neural network sensitivity analysis.
Validity of AI inferences should be a non-negotiable condition for deployment, not just an afterthought in regulatory frameworks.
