Search Results for author:
Found 30 papers, 14 papers with code
A Majorization-Minimization Gauss-Newton Method for 1-Bit Matrix Completion
In 1-bit matrix completion, the aim is to estimate an underlying low-rank matrix from a partial set of binary observations.
Distributed Sparse Linear Regression under Communication Constraints
In multiple domains, statistical tasks are performed in distributed settings, with data split among several end machines that are connected to a fusion center.
Recovery Guarantees for Distributed-OMP
We study distributed schemes for high-dimensional sparse linear regression, based on orthogonal matching pursuit (OMP).
Inductive Matrix Completion: No Bad Local Minima and a Fast Algorithm
The inductive matrix completion (IMC) problem is to recover a low rank matrix from few observed entries while incorporating prior knowledge about its row and column subspaces.
GNMR: A provable one-line algorithm for low rank matrix recovery
Low rank matrix recovery problems, including matrix completion and matrix sensing, appear in a broad range of applications.
Spectral Top-Down Recovery of Latent Tree Models
For large trees, a common approach, termed divide-and-conquer, is to recover the tree structure in two steps.
Distributed Sparse Normal Means Estimation with Sublinear Communication
We assume there are $M$ machines, each holding $d$-dimensional observations of a $K$-sparse vector $\mu$ corrupted by additive Gaussian noise.
Improved Convergence Guarantees for Learning Gaussian Mixture Models by EM and Gradient EM
In previous works, the required number of samples had a quadratic dependence on the maximal separation between the K components, and the resulting error estimate increased linearly with this maximal separation.
"Self-Wiener" Filtering: Data-Driven Deconvolution of Deterministic Signals
Specifically, our algorithm works in the frequency-domain, where it tries to mimic the optimal unrealizable non-linear Wiener-like filter as if the unknown deterministic signal were known.
The Trimmed Lasso: Sparse Recovery Guarantees and Practical Optimization by the Generalized Soft-Min Penalty
We present a new approach to solve the sparse approximation or best subset selection problem, namely find a $k$-sparse vector ${\bf x}\in\mathbb{R}^d$ that minimizes the $\ell_2$ residual $\lVert A{\bf x}-{\bf y} \rVert_2$.
Spectral neighbor joining for reconstruction of latent tree models
A common assumption in multiple scientific applications is that the distribution of observed data can be modeled by a latent tree graphical model.
Rank $2r$ iterative least squares: efficient recovery of ill-conditioned low rank matrices from few entries
We present a new, simple and computationally efficient iterative method for low rank matrix completion.
Optimization and Control
Beyond Trees: Classification with Sparse Pairwise Dependencies
The resulting classifier is linear in the log-transformed univariate and bivariate densities that correspond to the tree edges.
Learning Binary Latent Variable Models: A Tensor Eigenpair Approach
Latent variable models with hidden binary units appear in various applications.
SpectralNet: Spectral Clustering using Deep Neural Networks
Moreover, the map learned by SpectralNet naturally generalizes the spectral embedding to unseen data points.
Cost efficient gradient boosting
In contrast to previous approaches to learning with cost penalties, our method can grow very deep trees that on average are nonetheless cheap to compute.
On Detection of Faint Edges in Noisy Images
A fundamental question for edge detection in noisy images is how faint can an edge be and still be detected.
Unsupervised Ensemble Regression
Consider a regression problem where there is no labeled data and the only observations are the predictions $f_i(x_j)$ of $m$ experts $f_{i}$ over many samples $x_j$.
Minimax-optimal semi-supervised regression on unknown manifolds
We consider semi-supervised regression when the predictor variables are drawn from an unknown manifold.
A Deep Learning Approach to Unsupervised Ensemble Learning
We show how deep learning methods can be applied in the context of crowdsourcing and unsupervised ensemble learning.
Unsupervised Ensemble Learning with Dependent Classifiers
In unsupervised ensemble learning, one obtains predictions from multiple sources or classifiers, yet without knowing the reliability and expertise of each source, and with no labeled data to assess it.
Fast Detection of Curved Edges at Low SNR
Detecting edges is a fundamental problem in computer vision with many applications, some involving very noisy images.
Detecting the large entries of a sparse covariance matrix in sub-quadratic time
observations, it is typically estimated by the sample covariance matrix, at a computational cost of $O(np^{2})$ operations.
Learning Parametric-Output HMMs with Two Aliased States
In various applications involving hidden Markov models (HMMs), some of the hidden states are aliased, having identical output distributions.
Estimating the Accuracies of Multiple Classifiers Without Labeled Data
In various situations one is given only the predictions of multiple classifiers over a large unlabeled test data.
On the Optimality of Averaging in Distributed Statistical Learning
For both regimes and under suitable assumptions, we present asymptotically exact expressions for this estimation error.
Do semidefinite relaxations solve sparse PCA up to the information limit?
In fact, we conjecture that in the single-spike model, no computationally-efficient algorithm can recover a spike of $\ell_0$-sparsity $k\geq\Omega(\sqrt{n})$.
Ranking and combining multiple predictors without labeled data
This scenario is different from the standard supervised setting, where each classifier accuracy can be assessed using available labeled data, and raises two questions: given only the predictions of several classifiers over a large set of unlabeled test data, is it possible to a) reliably rank them; and b) construct a meta-classifier more accurate than most classifiers in the ensemble?
Statistical Analysis of Semi-Supervised Learning: The Limit of Infinite Unlabelled Data
We study the behavior of the popular Laplacian Regularization method for Semi-Supervised Learning at the regime of a fixed number of labeled points but a large number of unlabeled points.
Treelets--An adaptive multi-scale basis for sparse unordered data
In many modern applications, including analysis of gene expression and text documents, the data are noisy, high-dimensional, and unordered--with no particular meaning to the given order of the variables.
Methodology
