Constrained Machine Learning Through Hyperspherical Representation
This addresses the challenge of reliable constraint enforcement in ML for safety-critical applications, representing a novel method rather than an incremental improvement.
The paper tackled the problem of ensuring constraints satisfaction in machine learning outputs, especially for safety-critical domains, by introducing Hyperspherical Constrained Representation, which guarantees 100% constraint satisfaction with minimal computational cost at inference while maintaining comparable predictive performance.
The problem of ensuring constraints satisfaction on the output of machine learning models is critical for many applications, especially in safety-critical domains. Modern approaches rely on penalty-based methods at training time, which do not guarantee to avoid constraints violations; or constraint-specific model architectures (e.g., for monotonocity); or on output projection, which requires to solve an optimization problem that might be computationally demanding. We present the Hypersherical Constrained Representation, a novel method to enforce constraints in the output space for convex and bounded feasibility regions (generalizable to star domains). Our method operates on a different representation system, where Euclidean coordinates are converted into hyperspherical coordinates relative to the constrained region, which can only inherently represent feasible points. Experiments on a synthetic and a real-world dataset show that our method has predictive performance comparable to the other approaches, can guarantee 100% constraint satisfaction, and has a minimal computational cost at inference time.