MP4b.1

Detection of Untrustworthy Outputs from Learning Models: A Multiple Testing Approach

Akshayaa Magesh, Venugopal Veeravalli, UIUC, United States; Anirban Roy, Susmit Jha, SRI, United States
Session:
MP4b: Information Theoretic Methods for Machine Learning Lecture
Track:
Adaptive Systems, Machine Learning, and Data Analytics
Location:
Nautilus
Presentation Time:
Mon, 28 Oct, 15:30 - 15:55 PT (UTC -7)
Presentation
Discussion
Resources
No resources available.
Session MP4b
MP4b.1: Detection of Untrustworthy Outputs from Learning Models: A Multiple Testing Approach
Akshayaa Magesh, Venugopal Veeravalli, UIUC, United States; Anirban Roy, Susmit Jha, SRI, United States
MP4b.2: Enhancing Policy Robustness in Markov Decision Processes with Limited Domain Knowledge
Akram Awad, Shihab Ahmed, Yue Wang, George Atia, University of Central Florida, United States
MP4b.3: Adaptive Text Watermark for Large Language Models
Yepeng Liu, Yuheng Bu, University of Florida, United States
MP4b.4: Understanding global convergence in bilevel optimization
Quan Xiao, Tianyi Chen, Rensselaer Polytechnic Institute, United States
Contacts