Home

Person

Volkan Cevher

About
Privacy
Disclaimer

Graph Chatbot

Related publications (249)

MAP Estimation for Bayesian Mixture Models with Submodular Priors

Volkan Cevher, Marwa El Halabi, Luca Baldassarre

We propose a Bayesian approach where the signal structure can be represented by a mixture model with a submodular prior. We consider an observation model that leads to Lipschitz functions. Due to its combinatorial nature, computing the maximum a posteriori ...

2014

Learning non-parametric basis independent models from point queries via low-rank methods

Hemant Tyagi, Volkan Cevher

We consider the problem of learning multi-ridge functions of the form f (x) = g(Ax) from point evaluations of f. We assume that the function f is defined on an l(2)-ball in R-d, g is twice continuously differentiable almost everywhere, and A is an element ...

Elsevier2014

Model-based Sparse Component Analysis for Reverberant Speech Localization

Hervé Bourlard, Afsaneh Asaei, Mohammadjavad Taghizadeh, Volkan Cevher

In this paper, the problem of multiple speaker localization via speech separation based on model-based sparse recovery is studies. We compare and contrast computational sparse optimization methods incorporating harmonicity and block structures as well as a ...

2014

Manifold Sparse Beamforming

Afsaneh Asaei, Volkan Cevher, Baran Gözcü

We consider the minimum variance distortionless response (MVDR) beamforming problems where the array covariance matrix is rank deficient. The conventional approach handles such rank-deficiencies via diagonal loading on the covariance matrix. In this settin ...

2013

A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions

Volkan Cevher, Anastasios Kyrillidis, Quoc Tran Dinh

We propose an algorithmic framework for convex minimization problems of a composite function with two terms: a self-concordant function and a possibly nonsmooth regularization term. Our method is a new proximal Newton algorithm that features a local quadra ...

2013

Sparse projections onto the simplex

Volkan Cevher, Anastasios Kyrillidis, Christoph Koch

Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the`1-norm. However, several important learning applications cannot benet from this approach as they feature these convex no ...

JMLR W&CP2013

Energy-aware adaptive bi-Lipschitz embeddings

Volkan Cevher, Bubacarr Bah, Ali Sadeghian

We propose a dimensionality reducing matrix design based on training data with constraints on its Frobenius norm and number of rows. Our design criteria is aimed at preserving the distances between the data points in the dimensionality reduced space as muc ...

2013

To Convexify or Not? Regression with Clustering Penalties on Graphs

Volkan Cevher, Marwa El Halabi, Luca Baldassarre

We consider minimization problems that are compositions of convex functions of a vector

\x \in\reals^N

with submodular set functions of its support (i.e., indices of the non-zero coefficients of

\x

). Such problems are in general difficult for large

N

...

IEEE2013

Fast Proximal algorithms for Self-concordant function minimization with application to sparse graph selection

Volkan Cevher, Anastasios Kyrillidis

The convex

\ell_1

-regularized

\log\det

divergence criterion has been shown to produce theoretically consistent graph learning. However, this objective function is challenging since the

\ell_1

-regularization is nonsmooth, the

\log\det

objective is n ...

2013

Fast Proximal Algorithms For Self-Concordant Function Minimization With Application To Sparse Graph Selection

Volkan Cevher, Anastasios Kyrillidis

The convex l(1)-regularized log det divergence criterion has been shown to produce theoretically consistent graph learning. However, this objective function is challenging since the l(1)-regularization is nonsmooth, the log det objective is not globally Li ...

IEEE2013

High-Dimensional Gaussian Process Bandits

Volkan Cevher, Andreas Krause

Many applications in machine learning require optimizing unknown functions defined over a high-dimensional space from noisy samples that are expensive to obtain. We address this notoriously hard challenge, under the assumptions that the function varies onl ...

2013

Tractability of interpretability via selection of group-sparse models

Volkan Cevher, Luca Baldassarre, Nirav Bhan

Group-based sparsity models are proven instrumental in linear regression problems for recovering signals from much fewer measurements than standard compressive sensing. A promise of these models is to lead to “interpretable” signals for which we identify i ...

2013

Active Learning of Multi-Index Function Models

Hemant Tyagi, Volkan Cevher

We consider the problem of actively learning \textit{multi-index} functions of the form

f(x) = g(Ax)= \sum_{i=1}^k g_i(a_i^Tx)

from point evaluations of

f

. We assume that the function

f

is defined on an

\ell_2

-ball in

\Real^d

g

is twice contin ...

2012

Equivalence of synthesis and atomic formulations of sparse recovery

Volkan Cevher, Mitra Fatemi, Shayan Dashmiz

Recovery of sparse signals from linear, dimensionality reducing measurements broadly fall under two well-known formulations, named the synthesis and the analysis a ́ la Elad et al. Recently, Chandrasekaran et al. introduced a new algorithmic sparse recover ...

Ieee2012

Computational Methods For Structured Sparse Component Analysis of Convolutive Speech Mixtures

Hervé Bourlard, Afsaneh Asaei, Volkan Cevher

We cast the under-determined convolutive speech separation as sparse approximation of the spatial spectra of the mixing sources. In this framework we compare and contrast the major practical algorithms for structured sparse recovery of speech signal. Speci ...

2012

Learning Ridge Functions With Randomized Sampling In High Dimensions

Hemant Tyagi, Volkan Cevher

We study the problem of learning ridge functions of the form f(x) = g(aT x), x ∈ ℝd, from random samples. Assuming g to be a twice continuously differentiable function, we leverage techniques from low rank matrix recovery literature to derive a uniform app ...

IEEE2012

Hard Thresholding with Norm Constraints

Gilles Puy, Volkan Cevher, Anastasios Kyrillidis

We introduce a new sparse recovery paradigm, called Normed Pursuits, where efficient algorithms from combinatorial and convex optimization interface for interpretable and model-based solutions. Synthetic and real data experiments illustrate that Normed Pur ...

Ieee2012

Method, apparatus and computer program product for determining the location of a plurality of speech sources

Hervé Bourlard, Afsaneh Asaei, Volkan Cevher

The present invention discloses a method, apparatus and computer program product for determining the location of a plurality of speech sources in an area of interest, comprising performing an algorithm on a signal issued by either one of said plurality of ...

2012

Combinatorial Selection and Least Absolute Shrinkage via the CLASH Algorithm

Volkan Cevher, Anastasios Kyrillidis

The least absolute shrinkage and selection operator (LASSO) for linear regression exploits the geometric interplay of the

\ell_2

-data error objective and the

\ell_1

-norm constraint to arbitrarily select sparse models. Guiding this uninformed selection ...

IEEE2012

Filtered Variation method for denoising and sparse signal processing

Volkan Cevher

We propose a new framework, called Filtered Variation (FV), for denoising and sparse signal processing applications. These problems are inherently ill-posed. Hence, we provide regularization to overcome this challenge by using discrete time filters that ar ...

2012

Page 12 of 13