TIME
2024年12月17日(周二)10:00 – 11:00
VENUE
信管学院308会议室
SPEAKER
Lie He(贺烈) is a Machine Learning Researcher at Tencent. He earned his B.Sc. in Computational Mathematics from USTC and both his M.Sc. in Computational Science and Engineering and Ph.D. in Computer Science from the École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland. His research focuses on efficient large-scale stochastic optimization and robustness guarantees in the presence of training-time adversaries. A series of his publications have won him fellowships, grants, and industrial funding from Google. Besides, he has multiple research experiences at Google and Amazon.
TITLE
Towards Robust and Efficient Large-Scale Stochastic Optimization
ABSTRACT
The rapid advancements in machine learning have been driven by increasingly large datasets and growing computational power. Developing optimization algorithms that scale effectively with data size and the number of computing machines is critical but fraught with challenges, including computational bottlenecks and communication overhead. Additionally, large-scale stochastic optimization processes are inherently vulnerable to adversaries, such as corrupted training samples or compromised machines, which can significantly degrade model performance without robust safeguards. In this talk, I will delve into the dual challenges of efficiency and robustness in large-scale machine learning problems and present our recent work in addressing these issues, including novel approaches to scalable and resilient optimization.
编审:唐志皓 江波
欢迎 关注!