5 papers
Task-Aware Multi-Expert Architecture For Lifelong Deep Learning
Jianyu Wang, Jacob Nean-Hua Sheikh, Cat P. Le +1
Lifelong deep learning (LDL) trains neural networks to learn sequentially across tasks while preserving prior knowledge. We propose Task-Aware Multi-Expert (TAME), a continual lear…
FedGTEA: Federated Class-Incremental Learning with Gaussian Task Embedding and Alignment
Haolin Li, Hoda Bidkhori
We introduce a novel framework for Federated Class Incremental Learning, called Federated Gaussian Task Embedding and Alignment (FedGTEA). FedGTEA is designed to capture task-speci…
Robust Quickest Change Detection in Non-Stationary Processes
Yingze Hou, Yousef Oleyaeimotlagh, Rahul Mishra +2
Optimal algorithms are developed for robust detection of changes in non-stationary processes. These are processes in which the distribution of the data after change varies with tim…
Robust Quickest Change Detection with Sampling Control
Yingze Hou, Hoda Bidkhori, Taposh Banerjee
The problem of quickest detection of a change in the distribution of a sequence of random variables is studied. The objective is to detect the change with the minimum possible dela…
Robust Quickest Change Detection in Multi-Stream Non-Stationary Processes
Yingze Hou, Hoda Bidkhori, Taposh Banerjee
The problem of robust quickest change detection (QCD) in non-stationary processes under a multi-stream setting is studied. In classical QCD theory, optimal solutions are developed…