I'm an ELLIS PhD student at the Max Planck Institute for Intelligent Systems, supervised by Prof. Bernhard Schölkopf, Prof. Fanny Yang, and Prof. Amartya Sanyal. Prior to this, I completed an M.S. in Statistics at ETH Zürich and a B.S. in Mathematics and Economics at Nanyang Technological University.
I'm interested in understanding privacy risks in machine learning and developing methods to mitigate them, primarily through differential privacy and machine unlearning.
Publications
- Online Learning and Unlearning Yaxi Hu, Bernhard Schölkopf, Amartya Sanyal. Preprint
- Differentially Private Steering for Large Language Model Alignment Anmol Goel, Yaxi Hu, Iryna Gurevych, Amartya Sanyal. @ ICLR'2025
- Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation Amartya Sanyal, Yaxi Hu, Yaodong Yu, Yian Ma, Yixin Wang, Bernhard Schölkopf @ AISTATS'2025
- Provable privacy with non-private pre-processing Yaxi Hu, Amartya Sanyal, Bernhard Schölkopf @ ICML'2024
- PILLAR: How to make semi-private learning more effective Francesco Pinto, Yaxi Hu, Fanny Yang, Amartya Sanyal @ SaTML'2024
- How unfair is private learning? Amartya Sanyal*, Yaxi Hu*, Fanny Yang (Oral) @ UAI'2022
Yaxi Hu
yaxi.hu@tuebingen.mpg.de
Empirical Inference Department
Max Planck Institute for Intelligent Systems