
The Trimmed Lasso: Sparse Recovery Guarantees and Practical Optimization by the Generalized SoftMin Penalty
We present a new approach to solve the sparse approximation or best subs...
read it

Spectral neighbor joining for reconstruction of latent tree models
A key assumption in multiple scientific applications is that the distrib...
read it

Tight Recovery Guarantees for Orthogonal Matching Pursuit Under Gaussian Noise
Orthogonal Matching pursuit (OMP) is a popular algorithm to estimate an ...
read it

Semiparametric Classification of Forest Graphical Models
We propose a new semiparametric approach to binary classification that e...
read it

Learning Binary Latent Variable Models: A Tensor Eigenpair Approach
Latent variable models with hidden binary units appear in various applic...
read it

SpectralNet: Spectral Clustering using Deep Neural Networks
Spectral clustering is a leading and popular technique in unsupervised d...
read it

On Detection of Faint Edges in Noisy Images
A fundamental question for edge detection in noisy images is how faint c...
read it

Unsupervised Ensemble Regression
Consider a regression problem where there is no labeled data and the onl...
read it

Minimaxoptimal semisupervised regression on unknown manifolds
We consider semisupervised regression when the predictor variables are ...
read it

A Deep Learning Approach to Unsupervised Ensemble Learning
We show how deep learning methods can be applied in the context of crowd...
read it

Unsupervised Ensemble Learning with Dependent Classifiers
In unsupervised ensemble learning, one obtains predictions from multiple...
read it

Detecting the large entries of a sparse covariance matrix in subquadratic time
The covariance matrix of a pdimensional random variable is a fundamenta...
read it

Estimating the Accuracies of Multiple Classifiers Without Labeled Data
In various situations one is given only the predictions of multiple clas...
read it

On the Optimality of Averaging in Distributed Statistical Learning
A common approach to statistical learning with bigdata is to randomly s...
read it

Do semidefinite relaxations solve sparse PCA up to the information limit?
Estimating the leading principal components of data, assuming they are s...
read it

Ranking and combining multiple predictors without labeled data
In a broad range of classification and decision making problems, one is ...
read it

On learning parametricoutput HMMs
We present a novel approach for learning an HMM whose outputs are distri...
read it

Active Learning with Distributional Estimates
Active Learning (AL) is increasingly important in a broad range of appli...
read it