Utility–Separation Pareto Frontier: An Information-Theoretic Characterization
Published in Under review (Journal of Machine Learning Research — JMLR), 2025
Summary
This work studies how separation constraints relate to predictive utility through an information-theoretic lens, formalizing the feasible trade-off region and clarifying which operating points are attainable.
Resources
- Paper: (available on request / add link)
Recommended citation: Shizhou Xu. (2025). “Utility–Separation Pareto Frontier: An Information-Theoretic Characterization.” Under review at Journal of Machine Learning Research.
Download Paper | Download Slides