8 papers
AFA-BANDIT: Provably Near-Optimal Online Multi-Feature Classification Under Budget Constraints
AbdAlRahman Odeh, Teng-Hui Huang, Hesham El Gamal
Active Feature Acquisition (AFA) is a classification problem in which an agent decides which costly features to acquire before predicting each sample's label. Unlike batch AFA, whi…
High-Dimensional Bell States: A Paradigm Shift for Quantum Illumination
Armanpreet Pannu, Amr S. Helmy, Hesham El Gamal
This paper solves the open problem of characterizing the performance of quantum illumination (QI) with discrete variable states. By devising a novel quantum measurement approach al…
A novel multi-photon entangled state with enhanced resilience to path loss
Armanpreet Pannu, Amr S. Helmy, Hesham El Gamal
In the realm of quantum information, entanglement stands as a cornerstone phenomenon. It underpins a vast array of quantum information processes, offering significant potential for…
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…
Error Free Quantum Target Finding: When Sequential Detection Meets High Dimensional Entanglement
Armanpreet Pannu, Amr S. Helmy, Hesham El Gamal
We present a new method for target finding and ranging in Lidar applications using high-dimensional Bell states. Combined with a sequential decision rule, this scheme asymptoticall…
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…
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…
On the Multi-View Information Bottleneck Representation
Teng-Hui Huang, Aly El Gamal, Hesham El Gamal
In this work, we generalize the information bottleneck (IB) approach to the multi-view learning context. The exponentially growing complexity of the optimal representation motivate…