Counterexample-Guided Learning of Monotonic Neural Networks

Understand

The widespread adoption of deep learning is often attributed to its automatic feature construction with minimal inductive bias.

• However, in many real-world tasks, the learned function is intended to satisfy domain-specific constraints.
• We focus on monotonicity constraints, which are common and require that the function's output increases with increasing values of specific input features.
• We develop a counterexample-guided technique to provably enforce monotonicity constraints at prediction time.