no code implementations • 1 Jul 2023 • Ye Xue, Diego Klabjan, Jean Utke
In this work, we extend and improve Omninet, an architecture that is capable of handling multiple modalities and tasks at a time, by introducing cross-cache attention, integrating patch embeddings for vision inputs, and supporting structured data.
no code implementations • 4 Jun 2023 • Ye Xue, Vincent Lau
Based on our optimization formulation, we propose an alternating Riemannian optimization algorithm with a precoder that enables efficient OTA aggregation of low-rank local models without sacrificing training performance.
1 code implementation • 17 Aug 2021 • Ye Xue, Diego Klabjan, Yuan Luo
Federated learning is a distributed machine learning paradigm where multiple data owners (clients) collaboratively train one machine learning model while keeping data on their own devices.
1 code implementation • 21 Apr 2021 • Ye Xue, Vincent Lau, Songfu Cai
The proposed scheme leverages the global and local Riemannian geometry of the two-stage optimization problem and facilitates fast implementation for superb dictionary recovery performance by a finite number of samples without atom-by-atom calculation.
no code implementations • 2 Mar 2021 • Ye Xue, Vincent Lau
The proposed scheme includes a novel problem formulation and an efficient online algorithm design with convergence analysis.
no code implementations • 13 Jun 2020 • Ye Xue, Xuanyu Zheng, Vincent Lau
In this paper, we propose a holistic solution containing TO compensation, PHN estimation, precoder/decorrelator optimization of the LoS MIMO for wireless backhaul, and the interleaving of each part.
no code implementations • 26 Apr 2020 • Ye Xue, Yifei Shen, Vincent Lau, Jun Zhang, Khaled B. Letaief
Specifically, we propose a novel $\ell_3$-norm-based formulation to recover the data without channel estimation.
1 code implementation • 24 Feb 2020 • Yifei Shen, Ye Xue, Jun Zhang, Khaled B. Letaief, Vincent Lau
Dictionary learning is a classic representation learning method that has been widely applied in signal processing and data analytics.
1 code implementation • 12 Aug 2019 • Ye Xue, Diego Klabjan, Yuan Luo
The problem of missing values in multivariable time series is a key challenge in many applications such as clinical data mining.