Home

Person

Volkan Cevher

About
Privacy
Disclaimer

Graph Chatbot

Related publications (249)

A 5.9mW/Gb/s 7Gb/s/pin 8-Lane Single-Ended RX with Crosstalk Cancellation Scheme using a XCTLE and 56-tap XDFE in 32nm SOI CMOS

Yusuf Leblebici, Alessandro Cevrero, Lukas Kull, Volkan Cevher, Thomas Toifl, Cosimo Aprile, Ilter Ozkaya

This work reports an 8-lane single-ended RX featuring compact and low power far-end crosstalk (FEXT) cancellation circuits. The RX data-path consists of a cross continuous-time linear equalizer (XCTLE) to remove FEXT by nearest aggressors within the channe ...

2015

Composite Self-Concordant Minimization

Volkan Cevher, Anastasios Kyrillidis, Quoc Tran Dinh

We propose a variable metric framework for minimizing the sum of a self-concordant function and a possibly non-smooth convex function endowed with a computable proximal operator. We theoretically establish the convergence of our framework without relying o ...

Massachusetts Institute of Technology Press2015

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 function 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 heretofore ...

2015

Consistency of $\ell_1$-Regularized Maximum-Likelihood for Compressive Poisson Regression

Volkan Cevher, Yen-Huan Li

We consider Poisson regression with the canonical link function. This regression model is widely used in regression analysis involving count data; one important application in electrical engineering is transmission tomography. In this paper, we establish t ...

2015

A Universal Primal-Dual Convex Optimization Framework

Volkan Cevher, Quoc Tran Dinh, Alp Yurtsever

We propose a new primal-dual algorithmic framework for a prototypical con- strained convex optimization template. The algorithmic instances of our frame- work are universal since they can automatically adapt to the unknown Ho ̈lder con- tinuity properties ...

2015

What’s the Frequency, Kenneth?: Sublinear Fourier Sampling Off the Grid

Volkan Cevher, Yen-Huan Li

We design a sublinear Fourier sampling algorithm for a case of sparse off-grid frequency recovery. These are signals with the form f(t)=∑kj=1ajeiωjt+ν^ , t∈Z ; i.e., exponential polynomials with a noise term. The frequencies {ω j } satisfy ω j ∈ [η,2π − η ...

Springer Verlag2015

Signal Recovery and System Calibration from Multiple Compressive Poisson Measurements

Xin Yuan, Volkan Cevher

The measurement matrix employed in compressive sensing typically cannot be known precisely a priori, and must be estimated via calibration. One may take multiple compressive measurements, from which the measurement matrix and underlying signals may be esti ...

Siam Publications2015

Preconditioned Spectral Descent for Deep Learning

Volkan Cevher, Ya-Ping Hsieh, Edo Collins

Deep learning presents notorious computational challenges. These challenges in- clude, but are not limited to, the non-convexity of learning objectives and estimat- ing the quantities needed for optimization algorithms, such as gradients. While we do not a ...

2015

Barrier Smoothing for Nonsmooth Convex Minimization

Volkan Cevher, Yen-Huan Li, Quoc Tran Dinh

This paper proposes a smoothing technique for nonsmooth convex minimization using self-concordant barriers. To illustrate the main ideas, we compare our technique and the proximity smoothing approach (Nesterov2005) via the classical gradient method on both ...

Ieee2014

Convex Optimization for Big Data

Volkan Cevher

This article reviews recent advances in convex optimization algorithms for Big Data, which aim to reduce the computational, storage, and communications bottlenecks. We provide an overview of this emerging field, describe contemporary approximation techniqu ...

Institute of Electrical and Electronics Engineers2014

Metric Learning with Rank and Sparsity Constraints

Volkan Cevher, Baran Gözcü, Bubacarr Bah

Choosing a distance preserving measure or metric is fun- damental to many signal processing algorithms, such as k- means, nearest neighbor searches, hashing, and compressive sensing. In virtually all these applications, the efficiency of the signal process ...

Ieee2014

Matrix Recipes for Hard Thresholding Methods

Volkan Cevher, Anastasios Kyrillidis

In this paper, we present and analyze a new set of low-rank recovery algorithms for linear inverse problems within the class of hard thresholding methods. We provide strategies on how to set up these algorithms via basic ingredients for different configura ...

Springer Verlag2014

Time–Data Tradeoffs by Aggressive Smoothing

Volkan Cevher

This paper proposes a tradeoff between sample complexity and computation time that applies to statistical estimators based on convex optimization. As the amount of data increases, we can smooth optimization problems more and more aggressively to achieve ac ...

2014

Constrained convex minimization via model-based excessive gap

Volkan Cevher, Quoc Tran Dinh

We introduce a model-based excessive gap technique to analyze first-order primal- dual methods for constrained convex minimization. As a result, we construct new primal-dual methods with optimal convergence rates on the objective residual and the primal fe ...

2014

Scalable sparse covariance estimation via self-concordance

Volkan Cevher, Anastasios Kyrillidis, Rabeeh Karimi Mahabadi, Quoc Tran Dinh

We consider the class of convex minimization problems, composed of a self-concordant function, such as the logdet metric, a convex data fidelity term h and, a regularizing -- possibly non-smooth -- function g. This type of problems have recently attracted ...

2014

An inexact proximal path-following algorithm for constrained convex minimization

Volkan Cevher, Anastasios Kyrillidis, Quoc Tran Dinh

Many scientific and engineering applications feature large-scale non-smooth convex minimization problems over convex sets. In this paper, we address an important instance of this broad class where we assume that the non-smooth objective is equipped with a ...

Siam Publications2014

Bilinear Generalized Approximate Message Passing—Part II: Applications

Volkan Cevher

In this paper, we extend the generalized approximate message passing (G-AMP) approach, originally proposed for high-dimensional generalized-linear regression in the context of compressive sensing, to the generalized-bilinear case. In Part I of this two-par ...

Ieee-Inst Electrical Electronics Engineers Inc2014

Structured Sparsity Models for Reverberant Speech Separation

Hervé Bourlard, Mohammad Golbabaee, Afsaneh Asaei, Volkan Cevher

We tackle the multi-party speech recovery problem through modeling the acoustic of the reverberant chambers. Our approach exploits structured sparsity models to perform room modeling and speech recovery. We propose a scheme for characterizing the room acou ...

2014

Model-based Sketching and Recovery with Expanders

Volkan Cevher, Luca Baldassarre, Bubacarr Bah

Linear sketching and recovery of sparse vectors with randomly constructed sparse matrices has numerous applications in several areas, including compressive sensing, data stream computing, graph sketching, and combinatorial group testing. This paper conside ...

2014

Bilinear Generalized Approximate Message Passing—Part I: Derivation

Volkan Cevher

Institute of Electrical and Electronics Engineers2014

Page 11 of 13