David Inouye

David Inouye is an Assistant Professor in the Department of Electrical and Computer Engineering at Purdue University's College of Engineering. He received a B.S. in Natural Sciences from Covenant College, Georgia, and a B.S. in Electrical Engineering from Georgia Institute of Technology. He earned his Ph.D. in Computer Science from the University of Texas at Austin and completed a postdoctoral fellowship in machine learning at Carnegie Mellon University.

• B.S. in Natural Sciences, Covenant College, Georgia
• B.S. in Electrical Engineering, Georgia Institute of Technology
• Ph.D. in Computer Science, University of Texas at Austin
• Postdoc in Machine Learning, Carnegie Mellon University

Dr. Inouye's research focuses on the theoretical foundations of machine learning, particularly probabilistic models, invertible deep learning, and explainable artificial intelligence. He is pioneering work in destructive deep learning, with emphasis on generative models and density estimation. His research explores causal inference through invertible latent models, robustness in federated learning environments, and novel approaches to distribution matching and counterfactual analysis.

Recent publications highlight advancements in diffusion models, generative adversarial frameworks, and vertical federated learning architectures. Key trends include explainable AI techniques, robust learning under distribution shifts, and geometrically-aware probabilistic modeling. Notable contributions include PO-Flow for counterfactual sampling and Att-Adapter for attribute-controlled text-to-image generation.

• NSF Graduate Research Fellowship

Dr. Inouye's work bridges theoretical developments with practical implementations in dynamic computing environments, focusing on fault-tolerant systems and domain generalization challenges in distributed learning scenarios.