Search Results for author:
Found 9 papers, 4 papers with code
S-Omninet: Structured Data Enhanced Universal Multimodal Learning Architecture
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.
Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation
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.
Aggregation Delayed Federated Learning
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.
Efficient Sparse Coding using Hierarchical Riemannian Pursuit
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.
Online Orthogonal Dictionary Learning Based on Frank-Wolfe Method
The proposed scheme includes a novel problem formulation and an efficient online algorithm design with convergence analysis.
Line-of-Sight MIMO for High Capacity Millimeter Wave Backhaul in FDD Systems
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.
Blind Data Detection in Massive MIMO via $\ell_3$-norm Maximization over the Stiefel Manifold
Specifically, we propose a novel $\ell_3$-norm-based formulation to recover the data without channel estimation.
Complete Dictionary Learning via $\ell_p$-norm Maximization
Dictionary learning is a classic representation learning method that has been widely applied in signal processing and data analytics.
Mixture-based Multiple Imputation Model for Clinical Data with a Temporal Dimension
The problem of missing values in multivariable time series is a key challenge in many applications such as clinical data mining.
