4 papers
Stabilizing Transformer Training Through Consensus
Shyam Venkatasubramanian, Sean Moushegian, Michael Lin +3
Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various met…
Score-Based Quickest Change Detection and Fault Identification for Multi-Stream Signals
Wuxia Chen, Sean Moushegian, Vahid Tarokh +1
This paper introduces an approach to multi-stream quickest change detection and fault isolation for unnormalized and score-based statistical models. Traditional optimal algorithms…
Robust Score-Based Quickest Change Detection
Sean Moushegian, Suya Wu, Enmao Diao +3
Methods in the field of quickest change detection rapidly detect in real-time a change in the data-generating distribution of an online data stream. Existing methods have been able…
Diffusion-Based Hypothesis Testing and Change-Point Detection
Sean Moushegian, Taposh Banerjee, Vahid Tarokh
Score-based methods have recently seen increasing popularity in modeling and generation. Methods have been constructed to perform hypothesis testing and change-point detection with…