Dr. Mathias Lécuyer

Biography

Mathias Lécuyer is an Assistant Professor at the University of British Columbia, specializing in trustworthy artificial intelligence systems. His research focuses on enforcing provable guarantees in models and data ecosystems. Lécuyer has made significant contributions to several areas, tackling challenges that span effective caching in differentially-private databases, measuring the effects of training data on deep learning predictions, and enhancing adversarial robustness in AI models through techniques such as Randomized Smoothing. His foundational work on Randomized Smoothing has garnered over a thousand citations and serves as a critical building block for AI safety tools and fairness guarantees. Lécuier's recent projects include the development of causal machine learning models that inform downstream decisions and generalize the forecasting of actions within a training distribution. He has presented his work at prominent conferences, including AAAI and ICML, and actively contributes to the academic community as a reviewer for various journals.

Research Interests

Experience

Courses