Yusuf Sale
Papers
1
Total Citations
4
H-Index
1
About
Yusuf Sale is a rising researcher at the intersection of explainable artificial intelligence (XAI) and Bayesian optimization, whose work seeks to demystify black-box machine learning systems. His most-cited paper, "Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaboration" (2024), introduces a novel framework that leverages Shapley values to render the decisions of Bayesian optimization—traditionally opaque even to experts—transparent and interpretable. By bridging game-theoretic explanations with Gaussian process-based optimization, Sale enables human users to understand and trust why specific parameters are proposed, thereby fostering more effective human-AI collaboration in high-stakes black-box optimization tasks. Although early in his career, this work has already garnered 4 citations, signaling its timely relevance in the growing XAI community. Sale’s contributions address a critical gap: making advanced optimization algorithms not only powerful but also accountable. His research promises to shape how practitioners interact with automated decision-making systems, particularly in fields like hyperparameter tuning, experimental design, and automated machine learning. As an emerging voice in explainable and trustworthy AI, Yusuf Sale is poised to influence both theory and practice in human-centered optimization.
Research Focus
Key Achievements
Top Papers
- 1