2 citations · 3 across the 7 of their papers we have counts for
7 papers
Incomplete Multiview Learning via Wyner Common Information
AbdAlRahman Odeh, Teng-Hui Huang, Hesham El Gamal
Incomplete multiview clustering is of high recent interest, fueled by the advancement of common information-based deep multiview learning. The practical scenarios where unpaired mu…
An Efficient Difference-of-Convex Solver for Privacy Funnel
Teng-Hui Huang, Hesham El Gamal
We propose an efficient solver for the privacy funnel (PF) method, leveraging its difference-of-convex (DC) structure. The proposed DC separation results in a closed-form update eq…
Efficient Solvers for Wyner Common Information with Application to Multi-Modal Clustering
Teng-Hui Huang, Hesham El Gamal
We propose two novel extensions of the Wyner common information optimization problem. Each relaxes one fundamental constraints in Wyner's formulation. The \textit{Variational Wyner…
Efficient Alternating Minimization Solvers for Wyner Multi-View Unsupervised Learning
Teng-Hui Huang, Hesham El Gamal
In this work, we adopt Wyner common information framework for unsupervised multi-view representation learning. Within this framework, we propose two novel formulations that enable…
The Wyner Variational Autoencoder for Unsupervised Multi-Layer Wireless Fingerprinting
Teng-Hui Huang, Thilini Dahanayaka, Kanchana Thilakarathna +2
Wireless fingerprinting refers to a device identification method leveraging hardware imperfections and wireless channel variations as signatures. Beyond physical layer characterist…
A Linearly Convergent Douglas-Rachford Splitting Solver for Markovian Information-Theoretic Optimization Problems
Teng-Hui Huang, Aly El Gamal, Hesham El Gamal
In this work, we propose solving the Information bottleneck (IB) and Privacy Funnel (PF) problems with Douglas-Rachford Splitting methods (DRS). We study a general Markovian inform…
A Provably Convergent Information Bottleneck Solution via ADMM
Teng-Hui Huang, Aly El Gamal
The Information bottleneck (IB) method enables optimizing over the trade-off between compression of data and prediction accuracy of learned representations, and has successfully an…