Date & Time: 

  2025 /09 / 26  (Fri) 14:20 - 16:20

 

Location: 

  Delta Building R216, NTHU

 

Speaker: 

  黃昱智 教授

  國立陽明交通大學 電信工程研究所

 

Topic: 

  Quickest Mean-Change Detection via Confidence Sequence and Backward Sample Averages

 

Abstract: 

   In this talk, I will introduce BRAVO-CS, a novel approach to quickest mean-change detection (QMCD) in independent observation sequences where both pre-change and post-change distributions are unknown. BRAVO-CS works by recursively computing the backward sample average and identifying change points when the result escapes a forward confidence sequence. We will discuss how BRAVO-CS achieves an average detection delay that scales inversely with the magnitude of the mean shift, significantly improving upon existing methods, which exhibit inverse quadratic scaling for small shifts. Moreover, BRAVO-CS operates with linear time complexity, making it far more efficient than state-of-the-art techniques with quadratic complexity. Through theoretical insights and extensive simulations, we will demonstrate the robustness and effectiveness of BRAVO-CS, highlighting its potential for real-time mean-change detection in various applications.

This talk is based on joint work with Chih-Hsuan Li (NYCU) and Dr. Wen-Hsuan Li (NTPU).

 

Autobiography: 

    Yu-Chih Huang received his Ph.D. degree in electrical and computer engineering from Texas A&M University (TAMU) in 2013. From 2013 to 2015, he was a Postdoctoral Research Associate with TAMU. In 2015, he joined the Department of Communication Engineering, National Taipei University, Taiwan, as an Assistant Professor. Since 2020, He has been with the Institute of Communications Engineering, National Yang Ming Chiao Tung University, Taiwan, where he is currently a Professor. His research interests are in information theory, coding theory, wireless communications, and machine learning. He received the Y.Z. Hsu Scientific Paper Award in 2025, the National Science and Technology Council Wu Ta-You Memorial Award in 2023, the Ministry of Science and Technology Young Scholar Fellowship (Columbus Project) in 2020, and the 2018 IEEE Information Theory Society Taipei Chapter and IEEE Communications Society Taipei/Tainan Chapter’s Best Paper Award for Young Scholars. He is currently serving as an Associate Editor for IEEE Transactions on Communications and IEEE Communications Letters.