Search Results for author: Alfred O. Hero III

Found 43 papers, 3 papers with code

Iterative Sketching for Secure Coded Regression

no code implementations8 Aug 2023 Neophytos Charalambides, Hessam Mahdavifar, Mert Pilanci, Alfred O. Hero III

Specifically, we apply a random orthonormal matrix and then subsample \textit{blocks}, to simultaneously secure the information and reduce the dimension of the regression problem.


SOLBP: Second-Order Loopy Belief Propagation for Inference in Uncertain Bayesian Networks

no code implementations16 Aug 2022 Conrad D. Hougen, Lance M. Kaplan, Magdalena Ivanovska, Federico Cerutti, Kumar Vijay Mishra, Alfred O. Hero III

In second-order uncertain Bayesian networks, the conditional probabilities are only known within distributions, i. e., probabilities over probabilities.

Uncertain Bayesian Networks: Learning from Incomplete Data

no code implementations8 Aug 2022 Conrad D. Hougen, Lance M. Kaplan, Federico Cerutti, Alfred O. Hero III

When the historical data are limited, the conditional probabilities associated with the nodes of Bayesian networks are uncertain and can be empirically estimated.

Data Discovery Using Lossless Compression-Based Sparse Representation

no code implementations15 Mar 2021 Elyas Sabeti, Peter X. K. Song, Alfred O. Hero III

Sparse representation has been widely used in data compression, signal and image denoising, dimensionality reduction and computer vision.

Data Compression Dimensionality Reduction +1

Space-Time Adaptive Detection at Low Sample Support

no code implementations7 Oct 2020 Benjamin D. Robinson, Robert Malinas, Alfred O. Hero III

An important problem in space-time adaptive detection is the estimation of the large p-by-p interference covariance matrix from training signals.

The Power of Graph Convolutional Networks to Distinguish Random Graph Models: Short Version

no code implementations13 Feb 2020 Abram Magner, Mayank Baranwal, Alfred O. Hero III

We investigate the power of GCNs, as a function of their number of layers, to distinguish between different random graph models on the basis of the embeddings of their sample graphs.

Graph Representation Learning

Fundamental Limits of Deep Graph Convolutional Networks

no code implementations28 Oct 2019 Abram Magner, Mayank Baranwal, Alfred O. Hero III

We give a precise characterization of the set of pairs of graphons that are indistinguishable by a GCN with nonlinear activation functions coming from a certain broad class if its depth is at least logarithmic in the size of the sample graph.

Graph Classification Graph Representation Learning

Semi-supervised Learning in Network-Structured Data via Total Variation Minimization

no code implementations28 Jan 2019 Alexander Jung, Alfred O. Hero III, Alexandru Mara, Saeed Jahromi, Ayelet Heimowitz, Yonina C. Eldar

This lends naturally to learning the labels by total variation (TV) minimization, which we solve by applying a recently proposed primal-dual method for non-smooth convex optimization.


Scalable Mutual Information Estimation using Dependence Graphs

1 code implementation27 Jan 2018 Morteza Noshad, Yu Zeng, Alfred O. Hero III

To the best of our knowledge EDGE is the first non-parametric MI estimator that can achieve parametric MSE rates with linear time complexity.

Information Plane Mutual Information Estimation

Semiblind subgraph reconstruction in Gaussian graphical models

no code implementations15 Nov 2017 Tianpei Xie, Sijia Liu, Alfred O. Hero III

Consider a social network where only a few nodes (agents) have meaningful interactions in the sense that the conditional dependency graph over node attribute variables (behaviors) is sparse.

Rate-optimal Meta Learning of Classification Error

no code implementations31 Oct 2017 Morteza Noshad Iranzad, Alfred O. Hero III

Meta learning of optimal classifier error rates allows an experimenter to empirically estimate the intrinsic ability of any estimator to discriminate between two populations, circumventing the difficult problem of estimating the optimal Bayes classifier.

Classification Density Estimation +2

Direct Estimation of Information Divergence Using Nearest Neighbor Ratios

no code implementations17 Feb 2017 Morteza Noshad, Kevin R. Moon, Salimeh Yasaei Sekeh, Alfred O. Hero III

Considering the $k$-nearest neighbor ($k$-NN) graph of $Y$ in the joint data set $(X, Y)$, we show that the average powered ratio of the number of $X$ points to the number of $Y$ points among all $k$-NN points is proportional to R\'{e}nyi divergence of $X$ and $Y$ densities.

Similarity Function Tracking using Pairwise Comparisons

no code implementations7 Jan 2017 Kristjan Greenewald, Stephen Kelley, Brandon Oselio, Alfred O. Hero III

We propose Online Convex Ensemble StrongLy Adaptive Dynamic Learning (OCELAD), a general adaptive, online approach for learning and tracking optimal metrics as they change over time that is highly robust to a variety of nonstationary behaviors in the changing metric.

Clustering Metric Learning +1

Semi-Supervised Learning via Sparse Label Propagation

1 code implementation5 Dec 2016 Alexander Jung, Alfred O. Hero III, Alexandru Mara, Saeed Jahromi

This learning algorithm allows for a highly scalable implementation as message passing over the underlying data graph.

Scalable Semi-Supervised Learning over Networks using Nonsmooth Convex Optimization

no code implementations2 Nov 2016 Alexander Jung, Alfred O. Hero III, Alexandru Mara, Sabeur Aridhi

We propose a scalable method for semi-supervised (transductive) learning from massive network-structured datasets.

Transductive Learning

Multilayer Spectral Graph Clustering via Convex Layer Aggregation

no code implementations23 Sep 2016 Pin-Yu Chen, Alfred O. Hero III

Multilayer graphs are commonly used for representing different relations between entities and handling heterogeneous data processing tasks.

Clustering Graph Clustering +1

AMOS: An Automated Model Order Selection Algorithm for Spectral Graph Clustering

1 code implementation21 Sep 2016 Pin-Yu Chen, Thibaut Gensollen, Alfred O. Hero III

One of the longstanding problems in spectral graph clustering (SGC) is the so-called model order selection problem: automated selection of the correct number of clusters.

Clustering Graph Clustering +1

Information Theoretic Structure Learning with Confidence

no code implementations13 Sep 2016 Kevin R. Moon, Morteza Noshad, Salimeh Yasaei Sekeh, Alfred O. Hero III

Information theoretic measures (e. g. the Kullback Liebler divergence and Shannon mutual information) have been used for exploring possibly nonlinear multivariate dependencies in high dimension.

Two-sample testing

Learning Sparse Graphs Under Smoothness Prior

no code implementations12 Sep 2016 Sundeep Prabhakar Chepuri, Sijia Liu, Geert Leus, Alfred O. Hero III

Given the noisy data, we show that the joint sparse graph learning and denoising problem can be simplified to designing only the sparse edge selection vector, which can be solved using convex optimization.

Denoising Graph Learning

Multi-criteria Similarity-based Anomaly Detection using Pareto Depth Analysis

no code implementations20 Aug 2015 Ko-Jen Hsiao, Kevin S. Xu, Jeff Calder, Alfred O. Hero III

If the relative importance of the different dissimilarity measures are not known in advance, as in many anomaly detection applications, the anomaly detection algorithm may need to be executed multiple times with different choices of weights in the linear combination.

Anomaly Detection

Meta learning of bounds on the Bayes classifier error

no code implementations27 Apr 2015 Kevin R. Moon, Veronique Delouille, Alfred O. Hero III

For example, the Bayes error rate of a given feature space, if known, can be used to aid in choosing a classifier, as well as in feature selection and model selection for the base classifiers and the meta classifier.

feature selection Meta-Learning +1

Image patch analysis of sunspots and active regions. II. Clustering via matrix factorization

no code implementations10 Apr 2015 Kevin R. Moon, Veronique Delouille, Jimmy J. Li, Ruben De Visscher, Fraser Watson, Alfred O. Hero III

We also find that including data focused on the neutral line of an active region can result in an increased correspondence between our clustering results and other active region descriptors such as the Mount Wilson classifications and the $R$ value.

Clustering General Classification

Phase Transitions in Spectral Community Detection of Large Noisy Networks

no code implementations9 Apr 2015 Pin-Yu Chen, Alfred O. Hero III

We prove phase transitions in community detectability as a function of the external edge connection probability and the noisy edge presence probability under a general network model where two arbitrarily connected communities are interconnected by random external edges.

Clustering Community Detection

Multivariate f-Divergence Estimation With Confidence

no code implementations7 Nov 2014 Kevin R. Moon, Alfred O. Hero III

The problem of f-divergence estimation is important in the fields of machine learning, information theory, and statistics.

General Classification

MIST: L0 Sparse Linear Regression with Momentum

no code implementations25 Sep 2014 Goran Marjanovic, Magnus O. Ulfarsson, Alfred O. Hero III

Significant attention has been given to minimizing a penalized least squares criterion for estimating sparse solutions to large linear systems of equations.


L0 Sparse Inverse Covariance Estimation

no code implementations5 Aug 2014 Goran Marjanovic, Alfred O. Hero III

In this paper we consider non-convex $l_0$ penalized log-likelihood inverse covariance estimation and present a novel cyclic descent algorithm for its optimization.

Image patch analysis and clustering of sunspots: a dimensionality reduction approach

no code implementations24 Jun 2014 Kevin R. Moon, Jimmy J. Li, Veronique Delouille, Fraser Watson, Alfred O. Hero III

Sunspots, as seen in white light or continuum images, are associated with regions of high magnetic activity on the Sun, visible on magnetogram images.

Clustering Dimensionality Reduction

Learning Latent Variable Gaussian Graphical Models

no code implementations10 Jun 2014 Zhaoshi Meng, Brian Eriksson, Alfred O. Hero III

Gaussian graphical models (GGM) have been widely used in many high-dimensional applications ranging from biological and financial data to recommender systems.

Recommendation Systems

Kronecker PCA Based Spatio-Temporal Modeling of Video for Dismount Classification

no code implementations19 May 2014 Kristjan H. Greenewald, Alfred O. Hero III

We consider the application of KronPCA spatio-temporal modeling techniques [Greenewald et al 2013, Tsiligkaridis et al 2013] to the extraction of spatiotemporal features for video dismount classification.

Classification Dimensionality Reduction +2

Spectral Correlation Hub Screening of Multivariate Time Series

no code implementations13 Mar 2014 Hamed Firouzi, Dennis Wei, Alfred O. Hero III

This property permits independent correlation analysis at each frequency, alleviating the computational and statistical challenges of high-dimensional time series.

Time Series Time Series Analysis

Dynamic stochastic blockmodels for time-evolving social networks

no code implementations4 Mar 2014 Kevin S. Xu, Alfred O. Hero III

There has been recent interest in statistical modeling of dynamic networks, which are observed at multiple points in time and offer a richer representation of many complex phenomena.

Pareto-depth for Multiple-query Image Retrieval

no code implementations21 Feb 2014 Ko-Jen Hsiao, Jeff Calder, Alfred O. Hero III

Most content-based image retrieval systems consider either one single query, or multiple queries that include the same object or represent the same semantic information.

Content-Based Image Retrieval Information Retrieval +1

Nonlinear unmixing of hyperspectral images using a semiparametric model and spatial regularization

no code implementations31 Oct 2013 Jie Chen, Cédric Richard, Alfred O. Hero III

Incorporating spatial information into hyperspectral unmixing procedures has been shown to have positive effects, due to the inherent spatial-spectral duality in hyperspectral scenes.

Hyperspectral Unmixing

Kronecker Sum Decompositions of Space-Time Data

no code implementations27 Jul 2013 Kristjan Greenewald, Theodoros Tsiligkaridis, Alfred O. Hero III

To allow a smooth tradeoff between the reduction in the number of parameters (to reduce estimation variance) and the accuracy of the covariance approximation (affecting estimation bias), we introduce a diagonally loaded modification of the sum of kronecker products representation [1].

Revealing social networks of spammers through spectral clustering

no code implementations30 Apr 2013 Kevin S. Xu, Mark Kliger, Yilun Chen, Peter J. Woolf, Alfred O. Hero III

To date, most studies on spam have focused only on the spamming phase of the spam cycle and have ignored the harvesting phase, which consists of the mass acquisition of email addresses.


Dynamic stochastic blockmodels: Statistical models for time-evolving networks

no code implementations22 Apr 2013 Kevin S. Xu, Alfred O. Hero III

Significant efforts have gone into the development of statistical models for analyzing data in the form of networks, such as social networks.

Marginal Likelihoods for Distributed Parameter Estimation of Gaussian Graphical Models

no code implementations19 Mar 2013 Zhaoshi Meng, Dennis Wei, Ami Wiesel, Alfred O. Hero III

In this paper, we propose a general framework for distributed estimation based on a maximum marginal likelihood (MML) approach.

Covariance Estimation in High Dimensions via Kronecker Product Expansions

no code implementations12 Feb 2013 Theodoros Tsiligkaridis, Alfred O. Hero III

We show that a class of block Toeplitz covariance matrices is approximatable by low separation rank and give bounds on the minimal separation rank $r$ that ensures a given level of bias.

Vocal Bursts Intensity Prediction

Convergence Properties of Kronecker Graphical Lasso Algorithms

no code implementations3 Apr 2012 Theodoros Tsiligkaridis, Alfred O. Hero III, Shuheng Zhou

The KGlasso algorithm generalizes Glasso, introduced by Yuan and Lin ["Model selection and estimation in the Gaussian graphical model," Biometrika, vol.

Imputation Model Selection

Cannot find the paper you are looking for? You can Submit a new open access paper.