Towards Robust and Efficient Large-Scale Stochastic Optimization 发布时间:2024-11-20
- 活动时间:
- 活动地址:
- 主讲人:
题 目:Towards Robust and Efficient Large-Scale Stochastic Optimization
嘉 宾:Lie He, Applied Scientist, Tencent Inc.
主持人:刘慧康 副教授 金沙威尼斯欢乐娱人城
时 间:2024年12月2日(周一)14:00-15:30
地 点:金沙威尼斯欢乐娱人城 徐汇校区 安泰浩然楼308室
内容简介:
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.
演讲人简介:
Lie He 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.
欢迎广大师生参加!