12 papers
FlowMixer: A Depth-Agnostic Neural Architecture for Interpretable Spatiotemporal Forecasting
Fares B. Mehouachi, Saif Eddin Jabari
We introduce FlowMixer, a single-layer neural architecture that leverages constrained matrix operations to model structured spatiotemporal patterns with enhanced interpretability.…
Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless Norm Solution for Fast Adversarial Training
Fares B. Mehouachi, Saif Eddin Jabari
Adversarial training is a cornerstone of robust deep learning, but fast methods like the Fast Gradient Sign Method (FGSM) often suffer from Catastrophic Overfitting (CO), where mod…
Dynamic Mode Decomposition along Depth in Vision Transformers
Nishant Suresh Aswani, Saif Eddin Jabari
Recent work has shown that contiguous vision transformer (ViT) blocks (a) can be replaced by a linear map and (b) organize into recurrent phases of computation. We ask whether thes…
Backpressure-based Mean-field Type Game for Scheduling in Multi-Hop Wireless Sensor Networks
Salah Eddine Choutri, Boualem Djehiche, Prajwal Chauhan +1
We propose a Mean-Field Type Game (MFTG) framework for effective scheduling in multi-hop wireless sensor networks (WSNs) using backpressure as a performance criterion. Traditional…
Efficient Dilated Squeeze and Excitation Neural Operator for Differential Equations
Prajwal Chauhan, Salah Eddine Choutri, Saif Eddin Jabari
Fast and accurate surrogates for physics-driven partial differential equations (PDEs) are essential in fields such as aerodynamics, porous media design, and flow control. However,…
Monte Carlo-Type Neural Operator for Differential Equations
Salah Eddine Choutri, Prajwal Chauhan, Othmane Mazhar +1
The Monte Carlo-type Neural Operator (MCNO) introduces a framework for learning solution operators of one-dimensional partial differential equations (PDEs) by directly learning the…