Artificial Intelligence · Behavioral and Cognitive Science · Inverse Optimization
I am Ma ZhenYao (马镇尧; pronounced Ma Jen-Yow), a researcher in machine learning, human behavior, and inverse optimization. I am curious about, and my research focuses on:
I am currently an independent researcher and a Master's student at Xiamen University. I am seeking PhD or research opportunities related to AI, human behavior, business, and society. If you are interested in my research, please feel free to contact me.
Inspired by behavioral science, we propose Behavior Learning (BL), a novel general-purpose ML framework that learns (hierarchical) optimization structures from data, as a promising alternative to neural network for scientific domains involving optimization.
Many scientific phenomena can be modelled as outcomes of optimization. We introduce OptScientist, a novel automated framework for Optimization Scientific Law Discovery. OptScientist comprises a model that discovers compact symbolic optimization problems from data and an automated research agent that embeds the model in a loop of theory priors, law discovery, mechanism abstraction and new-data proposals. On OptFeynman, a novel benchmark of 99 physics-derived optimization problems, OptScientist recovers ground-truth laws on over 80% of tasks and remains robust to context noise. In two real-world tasks, it discovers symbolic optimization laws for human risky choice and central-bank monetary policy, achieving state-of-the-art-level held-out performance with near-minimal parameter counts.
Social preferences capture human motives beyond self-interest, such as kindness and moral concern. In this, we develop a rational-choice framework that can explain why behavior might appear selfish in some contexts while pro-social in others, even if the underlying social preferences themselves are stable.