Fanny Yang

Fanny Yang is an Assistant Professor in the Department of Computer Science at ETH Zurich. Her research focuses on machine learning (theory and reliability), non-parametric and high-dimensional statistics, and optimisation. She is affiliated with ETH Zurich's Computer Science department and maintains a profile page at the provided website. No existing biography is available for her.

Fanny Yang is a researcher at ETH Zurich with expertise in Machine Learning, Statistical Learning, Optimization, and High-dimensional Statistics. Her work explores the theoretical and practical challenges in learning algorithms, particularly focusing on generalization, robustness, and fairness. She investigates how adversarial training affects model performance, the trade-offs between robustness and accuracy, and the role of inductive bias in learning. Her research also addresses domain adaptation, label shifts, and the limitations of high-dimensional models. Yang's contributions include analyzing the impact of regularization, early stopping, and invariance-inducing techniques on model performance. Her publications highlight the importance of understanding the interplay between statistical and computational guarantees in learning algorithms.