Abstract
https://asmeet.webex.com/asmeet/j.php?MTID=m0c99a0fdab456e06b76d6621e21e9396
2024年8月26日星期一 上午 10:00 | 2 小時 | (UTC+08:00)台北
會議號: 2512 686 5892
密碼: viJDReFv479
As machine learning continues to revolutionize various domains, its integration with causal inference presents both novel opportunities and challenges. This talk explores the synergy between causality and machine learning, shedding light on how these two fields can complement each other to address complex questions that go beyond mere correlation.
The presentation will begin by discussing how machine learning can benefit causal analysis, alongside the challenges faced in industrial applications. I will present our recent progress in addressing these issues and elaborate on the potential impacts of our work. The second part of the talk will focus on introducing causation into model learning to enhance interpretability, robustness, and generalizability. I will also present our latest works achieving state-of-the-art results in this field.
2024年8月26日星期一 上午 10:00 | 2 小時 | (UTC+08:00)台北
會議號: 2512 686 5892
密碼: viJDReFv479
As machine learning continues to revolutionize various domains, its integration with causal inference presents both novel opportunities and challenges. This talk explores the synergy between causality and machine learning, shedding light on how these two fields can complement each other to address complex questions that go beyond mere correlation.
The presentation will begin by discussing how machine learning can benefit causal analysis, alongside the challenges faced in industrial applications. I will present our recent progress in addressing these issues and elaborate on the potential impacts of our work. The second part of the talk will focus on introducing causation into model learning to enhance interpretability, robustness, and generalizability. I will also present our latest works achieving state-of-the-art results in this field.
Bio
Keng-Te Liao received his Ph.D. in computer science from National Taiwan University in 2023. Before this he received his B.S. and M.S. degrees from National Chiao Tung University in 2011 and 2013. He was also a Research Intern at Microsoft Research and a Data Scientist Intern at Appier. His research focuses on probabilistic machine learning and causal inference. His recent research projects include deep Bayesian inference for multimodal learning, developing statistically efficient causal effect estimators, algorithmic recourse, and designing novel invariant learning algorithms.