172 citations · 516 across the 28 of their papers we have counts for
7 papers · 1 filter
Graph Signal Processing: Modulation, Convolution, and Sampling
John Shi, Jose M. F. Moura
To analyze data supported by arbitrary graphs G, DSP has been extended to Graph Signal Processing (GSP) by redefining traditional DSP concepts like shift, filtering, and Fourier tr…
Primal-dual methods for large-scale and distributed convex optimization and data analytics
Dusan Jakovetic, Dragana Bajovic, Joao Xavier +1
The augmented Lagrangian method (ALM) is a classical optimization tool that solves a given "difficult" (constrained) problem via finding solutions of a sequence of "easier"(often u…
Resilient Distributed Recovery of Large Fields
Yuan Chen, Soummya Kar, José M. F. Moura
This paper studies the resilient distributed recovery of large fields under measurement attacks, by a team of agents, where each measures a small subset of the components of a larg…
Explainable Machine Learning in Deployment
Umang Bhatt, Alice Xiang, Shubham Sharma +7
Explainable machine learning offers the potential to provide stakeholders with insights into model behavior by using various methods such as feature importance scores, counterfactu…
Forecaster: A Graph Transformer for Forecasting Spatial and Time-Dependent Data
Yang Li, José M. F. Moura
Spatial and time-dependent data is of interest in many applications. This task is difficult due to its complex spatial dependency, long-range temporal dependency, data non-stationa…
Resilient Distributed Field Estimation
Yuan Chen, Soummya Kar, José M. F. Moura
We study resilient distributed field estimation under measurement attacks. A network of agents or devices measures a large, spatially distributed physical field parameter. An adver…
On Network Science and Mutual Information for Explaining Deep Neural Networks
Brian Davis, Umang Bhatt, Kartikeya Bhardwaj +2
In this paper, we present a new approach to interpret deep learning models. By coupling mutual information with network science, we explore how information flows through feedforwar…