1 citations · 2 across the 4 of their papers we have counts for
4 papers
Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients
Minh Duong Nguyen, Khanh Le, Khoi Do +4
In personalized Federated Learning (pFL), high data heterogeneity can cause significant gradient divergence across devices, adversely affecting the learning process. This divergenc…
Levinson's theorem for two-dimensional scattering systems: it was a surprise, it is now topological!
A. Alexander, D. T. Nguyen, A. Rennie +1
We prove a general Levinson's theorem for Schrödinger operators in two dimensions with threshold obstructions at zero energy. Our results confirm and simplify earlier seminal resul…
Efficient and Accurate Learning of Mixtures of Plackett-Luce Models
Duc Nguyen, Anderson Y. Zhang
Mixture models of Plackett-Luce (PL) -- one of the most fundamental ranking models -- are an active research area of both theoretical and practical significance. Most previously pr…
Orthogonal Gated Recurrent Unit with Neumann-Cayley Transformation
Edison Mucllari, Vasily Zadorozhnyy, Cole Pospisil +2
In recent years, using orthogonal matrices has been shown to be a promising approach in improving Recurrent Neural Networks (RNNs) with training, stability, and convergence, partic…