Federico Croppi
Papers
1
Total Citations
4
H-Index
1
About
Federico Croppi is a researcher at the intersection of human-AI collaboration and explainable machine learning, with a primary focus on making Bayesian optimization (BO) more transparent and interpretable. His most cited work, "Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaboration" (2024, 4 citations), addresses a critical paradox in the field: while BO with Gaussian processes is a cornerstone algorithm for black-box optimization, it often remains a "black box" itself, offering little insight into why specific parameters are proposed. Croppi’s key contribution lies in integrating Shapley values—a game-theoretic explanation method—into the BO framework, enabling practitioners to understand the rationale behind parameter suggestions. This breakthrough not only demystifies the optimization process but also fosters more effective human-AI collaboration by allowing users to trust and refine algorithmic recommendations. Though early in his career, Croppi’s work has already garnered attention for bridging the gap between complex optimization algorithms and practical, user-centric AI systems. His research holds significant promise for fields ranging from automated machine learning to engineering design, where interpretability is as crucial as performance.
Research Focus
Key Achievements
Top Papers
- 1