<ul><li>The problem of ensuring constraints satisfaction on the output of machine learning models is critical for many applications, especially in safety-critical domains.</li><li>A novel method called Hypersherical Constrained Representation is proposed to enforce constraints in the output space for convex and bounded feasibility regions.</li><li>The method operates on a different representation system, where Euclidean coordinates are converted into hyperspherical coordinates relative to the constrained region, thereby ensuring only feasible points are represented.</li><li>Experiments on synthetic and real-world datasets show that the proposed method achieves comparable predictive performance, guarantees 100% constraint satisfaction, and has minimal computational cost at inference time.</li></ul>

Constrained Machine Learning Through Hyperspherical Representation

Discover more