Home

Person

Volkan Cevher

About
Privacy
Disclaimer

Graph Chatbot

Related publications (249)

Partial Recovery Bounds for the Sparse Stochastic Block Model

In this paper, we study the information-theoretic limits of community detection in the symmetric two-community stochastic block model, with intra-community and inter-community edge probabilities

\frac{a}{n}

and

\frac{b}{n}

respectively. We consider the ...

Ieee2016

Adaptive-Rate Sparse Signal Reconstruction With Application in Compressive Foreground Subtraction

Volkan Cevher

We propose and analyze an online algorithm for reconstructing a sequence of signals from a limited number of linear measurements. The signals are assumed sparse, with unknown support, and evolve over time according to a generic nonlinear dynamical model. O ...

Institute of Electrical and Electronics Engineers2016

Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation

Volkan Cevher, Ilija Bogunovic, Jonathan Mark Scarlett, Andreas Krause

We present a new algorithm, truncated variance reduction (TruVaR), that treats Bayesian optimization (BO) and level-set estimation (LSE) with Gaussian processes in a unified fashion. The algorithm greedily shrinks a sum of truncated variances within a set ...

2016

Stochastic Three-Composite Convex Minimization

Volkan Cevher, Alp Yurtsever, Cong Bang Vu

We propose a stochastic optimization method for the minimization of the sum of three convex functions, one of which has Lipschitz continuous gradient as well as restricted strong convexity. Our approach is most suitable in the setting where it is computati ...

2016

Time-Varying Gaussian Process Bandit Optimization

Volkan Cevher, Ilija Bogunovic, Jonathan Mark Scarlett

We consider the sequential Bayesian optimization problem with bandit feedback, adopting a formulation that allows for the reward function to vary with time. We model the reward function using a Gaussian process whose evolution obeys a simple Markov model. ...

2016

Binary Sparse Coding of Convolutive Mixtures for Sound Localization and Separation via Spatialization

Hervé Bourlard, Afsaneh Asaei, Mohammadjavad Taghizadeh, Volkan Cevher, Saeid Haghighatshoar

We propose a sparse coding approach to address the problem of source-sensor localization and speech reconstruction. This approach relies on designing a dictionary of spatialized signals by projecting the microphone array recordings into the array manifolds ...

Institute of Electrical and Electronics Engineers2016

Adaptive-Rate Reconstruction of Time-Varying Signals with Application in Compressive Foreground Extraction

Volkan Cevher

Institute of Electrical and Electronics Engineers2016

Frank-Wolfe Works for Non-Lipschitz Continuous Gradient Objectives: Scalable Poisson Phase Retrieval

Volkan Cevher, Marwa El Halabi, Yen-Huan Li, Quoc Tran Dinh, Alp Yurtsever, Ya-Ping Hsieh, Gergely Odor

We study a phase retrieval problem in the Poisson noise model. Motivated by the PhaseLift approach, we approximate the maximum-likelihood estimator by solving a convex program with a nuclear norm constraint. While the Frank-Wolfe algorithm, together with t ...

Ieee2016

Convex block-sparse linear regression with expanders - provably

Volkan Cevher, Anastasios Kyrillidis, Luca Baldassarre, Bubacarr Bah, Quoc Tran Dinh

Sparse matrices are favorable objects in machine learning and optimization. When such matrices are used, in place of dense ones, the overall complexity requirements in optimization can be significantly reduced in practice, both in terms of space and run-ti ...

2016

Composite convex minimization involving self-concordant-like cost functions

Volkan Cevher, Yen-Huan Li, Quoc Tran Dinh

The self-concordant-like property of a smooth convex func- tion is a new analytical structure that generalizes the self-concordant notion. While a wide variety of important applications feature the self- concordant-like property, this concept has heretofor ...

2015

A totally unimodular view of structured sparsity

Volkan Cevher, Marwa El Halabi

This paper describes a simple framework for structured sparse recovery based on convex optimization. We show that many interesting structured sparsity models can be naturally represented by linear matrix inequalities on the support of the unknown parameter ...

2015

Limits on Support Recovery with Probabilistic Models: An Information-Theoretic Framework

Volkan Cevher, Jonathan Mark Scarlett

The support recovery problem consists of deter- mining a sparse subset of a set of variables that is relevant in generating a set of observations, and arises in a diverse range of settings such as group testing, compressive sensing, and subset selection in ...

2015

A Primal-dual Framework For Mixtures Of Regularisers

Volkan Cevher, Baran Gözcü, Cosimo Aprile, Luca Baldassarre, Quoc Tran Dinh

Effectively solving many inverse problems in engineering requires to leverage all possible prior information about the structure of the signal to be estimated. This often leads to tackling constrained optimization problems with mixtures of regularizers. Pr ...

2015

Designing Statistical Estimators That Balance Sample Size, Risk, and Computational Cost

Volkan Cevher

This paper proposes a tradeoff between computational time, sample complexity, and statistical accuracy that applies to statistical estimators based on convex optimization. When we have a large amount of data, we can exploit excess samples to decrease stati ...

Ieee-Inst Electrical Electronics Engineers Inc2015

Scalable Convex Methods for Phase Retrieval

Volkan Cevher, Alp Yurtsever, Ya-Ping Hsieh

This paper describes scalable convex optimization methods for phase retrieval. The main characteristics of these methods are the cheap per-iteration complexity and the low-memory footprint. With a variant of the original PhaseLift formulation, we first ill ...

2015

Active Learning of Self-concordant like Multi-index Functions

Volkan Cevher, Ilija Bogunovic, Jonathan Mark Scarlett

We study the problem of actively learning a multi-index function of the form f (x) = g_0 (A_0 x) from its point evaluations, where A_0 ∈ R_{k×d} with k ≪ d. We build on the assumptions and techniques of an existing approach based on low-rank matrix recover ...

2015

Sparsistency of $\ell_1$-Regularized $M$-Estimators

Volkan Cevher, Yen-Huan Li, Jonathan Mark Scarlett

We consider the model selection consistency or sparsistency of a broad set of

\ell_1

-regularized

M

-estimators for linear and non-linear statistical models in a unified fashion. For this purpose, we propose the local structured smoothness condition (LSS ...

2015

Introduction to the Issue on Signal Processing for Big Data

Volkan Cevher

Ieee-Inst Electrical Electronics Engineers Inc2015

Sparse Group Covers and Greedy Tree Approximations

Volkan Cevher, Luca Baldassarre

We consider the problem of finding a K-sparse approximation of a signal, such that the support of the approximation is the union of sets from a given collection, a.k.a. group structure. This problem subsumes the one of finding K-sparse tree approximations. ...

2015

Structured Sampling and Recovery of iEEG Signals

Yusuf Leblebici, Volkan Cevher, Mahsa Shoaran, Cosimo Aprile, Luca Baldassarre

Wireless implantable devices capable of monitoring the electrical activity of the brain are becoming an important tool for understanding, and potentially treating, mental diseases such as epilepsy and depression. Compressive sensing (CS) is emerging as a p ...

2015

Page 10 of 13