Frederick Eberhardt

Papers

Total Citations

H-Index

About

Frederick Eberhardt is a leading figure in causal inference and machine learning, whose work bridges rigorous statistical theory with practical applications in artificial intelligence and cognitive science. His research focuses on causal discovery from observational and experimental data, developing algorithms that uncover cause-effect relationships without requiring controlled interventions. A major contribution is his foundational work on "Visual Causal Feature Learning," where he provides a formal definition of visual causation—a framework that generalizes causal learning to settings where causal variables must be inferred from high-dimensional sensory data, applicable to humans, animals, and robots. This paper, with 48 citations, has influenced both computational and cognitive approaches to understanding how perception drives causal reasoning. Eberhardt’s broader impact is evident in his highly cited work on causal structure learning and the design of experiments for causal discovery, which has shaped modern approaches in fields from neuroscience to genomics. His achievements include pioneering methods for integrating causal inference with deep learning, and his research continues to advance how machines and humans learn causal relationships from complex, real-world data.