1 citations · 1 across the 10 of their papers we have counts for
13 papers
Colored Graph Signal Diffusion Models
Yiğit Berkay Uslu, Samar Hadou, Shirin Saeedi Bidokhti +1
Standard diffusion processes with isotropic noise corruption are not spectrally neutral. They inherit a coarse-to-fine generation hierarchy from the nonuniform data spectrum, becau…
Generative Diffusion Models of Stochastic Graph Signals
Yiğit Berkay Uslu, Samar Hadou, Sergio Rozada +2
Sampling stochastic signals supported on a graph underlies many graph machine learning tasks, including recommender systems, forecasting in financial markets, and wireless network…
Constrained Diffusion Models with Primal-Dual Inference
Samar Hadou, Yigit Berkay Uslu, Alejandro Ribeiro
This paper develops constrained diffusion models with primal-dual inference (PDI) to sample from optimal distributions of entropy-regularized optimization problems with \emph{avera…
Graph Signal Diffusion Models for Wireless Resource Allocation
Yigit Berkay Uslu, Samar Hadou, Shirin Saeedi Bidokhti +1
We consider constrained ergodic resource optimization in wireless networks with graph-structured interference. We train a diffusion model policy to match expert conditional distrib…
Unrolled Neural Networks for Constrained Optimization
Samar Hadou, Alejandro Ribeiro
We develop unrolled neural networks to solve constrained optimization problems, offering accelerated, learnable counterparts to dual ascent (DA) algorithms. Our framework, termed c…
A Constrained Optimization Perspective of Unrolled Transformers
Javier Porras-Valenzuela, Samar Hadou, Alejandro Ribeiro
We introduce a constrained optimization framework for training transformers that behave like optimization descent algorithms. Specifically, we enforce layerwise descent constraints…
Graph Signal Generative Diffusion Models
Yigit Berkay Uslu, Samar Hadou, Sergio Rozada +2
We introduce U-shaped encoder-decoder graph neural networks (U-GNNs) for stochastic graph signal generation using denoising diffusion processes. The architecture learns node featur…
Unrolled Graph Neural Networks for Constrained Optimization
Samar Hadou, Alejandro Ribeiro
In this paper, we unroll the dynamics of the dual ascent (DA) algorithm in two coupled graph neural networks (GNNs) to solve constrained optimization problems. The two networks int…
Generative Diffusion Models for Resource Allocation in Wireless Networks
Yigit Berkay Uslu, Samar Hadou, Shirin Saeedi Bidokhti +1
This paper proposes a supervised training algorithm for learning stochastic resource allocation policies with generative diffusion models (GDMs). We formulate the allocation proble…
Robust Stochastically-Descending Unrolled Networks
Samar Hadou, Navid NaderiAlizadeh, Alejandro Ribeiro
Deep unrolling, or unfolding, is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network. However, the conv…
Stochastic Unrolled Federated Learning
Samar Hadou, Navid NaderiAlizadeh, Alejandro Ribeiro
Algorithm unrolling has emerged as a learning-based optimization paradigm that unfolds truncated iterative algorithms in trainable neural-network optimizers. We introduce Stochasti…
Space-Time Graph Neural Networks with Stochastic Graph Perturbations
Samar Hadou, Charilaos Kanatsoulis, Alejandro Ribeiro
Space-time graph neural networks (ST-GNNs) are recently developed architectures that learn efficient graph representations of time-varying data. ST-GNNs are particularly useful in…
Space-Time Graph Neural Networks
Samar Hadou, Charilaos I. Kanatsoulis, Alejandro Ribeiro
We introduce space-time graph neural network (ST-GNN), a novel GNN architecture, tailored to jointly process the underlying space-time topology of time-varying network data. The co…