@inproceedings{6db2d87a8423470db74691a583981ed5,
title = "Opportunities and challenges in learning to bound",
abstract = "Parameter estimation performance bounds serve as valuable tools in statistical signal processing, yet deriving them traditionally requires full knowledge of the data distribution. Recently, a framework has been proposed that combines a generative model with estimation performance bounds, thus eliminating the need for full knowledge of the data distribution by learning it from data. We refer to this approach as learning-to-bound (L2B). In this paper, we offer a comprehensive review of recent developments and emphasize their advantages. We then dive into open challenges and future directions within the L2B framework. Lastly, we explore a different perspective - the application of estimation performance bounds to deep learning.",
keywords = "deep learning, Estimation performance bound",
author = "Habi, {Hai Victor} and Hagit Messer and Yoram Bresler",
note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 59th Annual Conference on Information Sciences and Systems, CISS 2025 ; Conference date: 19-03-2025 Through 21-03-2025",
year = "2025",
doi = "10.1109/CISS64860.2025.10944700",
language = "English (US)",
series = "2025 59th Annual Conference on Information Sciences and Systems, CISS 2025",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2025 59th Annual Conference on Information Sciences and Systems, CISS 2025",
address = "United States",
}