Just-in-Time Piecewise-Linear Semantics for ReLU-type Networks

Hongyi Duan, Yiyi Wang, Haoyang Liu, ZhangJian'an, FengRui Liu

Keywords: Neural Networks, Verification, Scalability, Trustworthy AI

Abstract: We present a JIT PL semantics for ReLU‑type networks that compiles models into a guarded CPWL transducer with shared guards. The system adds hyperplanes only when operands are affine on the current cell, maintains global lower/upper envelopes, and uses a budgeted branch‑and‑bound. We obtain anytime soundness, exactness on fully refined cells, monotone progress, guard‑linear complexity (avoiding global $\binom{k}{2}$), dominance pruning, and decidability under finite refinement. The shared carrier supports region extraction, decision complexes, Jacobians, exact/certified Lipschitz, LP/SOCP robustness, and maximal causal influence. A minimal prototype returns certificates or counterexamples with cost proportional to visited subdomains.

Primary Area: interpretability and explainable AI

Submission Number: 11015