Home

Person

Volkan Cevher

About
Privacy
Disclaimer

Graph Chatbot

Related publications (249)

Page 4 of 13

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

Learning-Based Compressive MRI

Volkan Cevher, Jonathan Mark Scarlett, Yen-Huan Li, Baran Gözcü, Rabeeh Karimi Mahabadi

In the area of magnetic resonance imaging (MRI), an extensive range of non-linear reconstruction algorithms have been proposed that can be used with general Fourier subsampling patterns. However, the design of these subsampling patterns has typically been ...

Institute of Electrical and Electronics Engineers2018

Limits on Sparse Support Recovery via Linear Sketching with Random Expander Matrices

Volkan Cevher, Jonathan Mark Scarlett

Linear sketching is a powerful tool for the problem of sparse signal recovery, having numerous applications such as compressive sensing, data stream computing, graph sketching, and routing. Motivated by applications where the \emph{positions} of the non-ze ...

2016

Truly No-Regret Learning in Constrained MDPs

Volkan Cevher

Constrained Markov decision processes (CMDPs) are a common way to model safety constraints in reinforcement learning. State-of-the-art methods for efficiently solving CMDPs are based on primal-dual algorithms. For these algorithms, all currently known regr ...

2024

DiGress: Discrete Denoising diffusion for graph generation

Pascal Frossard, Volkan Cevher, Igor Krawczuk, Clément Arthur Yvon Vignac, Bohan Wang

This work introduces DiGress, a discrete denoising diffusion model for generating graphs with categorical node and edge attributes. Our model utilizes a discrete diffusion process that progressively edits graphs with noise, through the process of adding or ...

2023

Dimension-free Information Concentration via Exp-Concavity

Volkan Cevher, Ya-Ping Hsieh

Information concentration of probability measures have important implications in learning theory. Recently, it is discovered that the information content of a log-concave distribution concentrates around their differential entropy, albeit with an unpleasan ...

2018

On the Double Descent of Random Features Models Trained with SGD

Volkan Cevher, Fanghui Liu

We study generalization properties of random features (RF) regression in high dimensions optimized by stochastic gradient descent (SGD) in under-/overparameterized regime. In this work, we derive precise non-asymptotic error bounds of RF regression under b ...

2022

Estimation Error of the Constrained Lasso

Volkan Cevher, Ya-Ping Hsieh, Yen-Huan Li, Nissim Zerbib

This paper presents a non-asymptotic upper bound for the estimation error of the constrained lasso, under the high-dimensional (

n \ll p

) setting. In contrast to existing results, the error bound in this paper is sharp, is valid when the parameter to be e ...

2016

Efficient Continual Finite-Sum Minimization

Ioannis Mavrothalassitis, Volkan Cevher, Leello Tadesse Dadi, Efstratios Panteleimon Skoulakis

Given a sequence of functions

f_1,\ldots,f_n

with

f_i:\mathcal{D}\mapsto \mathbb{R}

, finite-sum minimization seeks a point

{x}^\star \in \mathcal{D}

minimizing

\sum_{j=1}^nf_j(x)/n

. In this work, we propose a key twist into the finite-sum minimizat ...

2024

Sifting through the Noise: Universal First-Order Methods for Stochastic Variational Inequalities

Volkan Cevher, Ali Kavis, Kimon Antonakopoulos, Thomas Michaelsen Pethick

We examine a flexible algorithmic framework for solving monotone variational inequalities in the presence of randomness and uncertainty. The proposed template encompasses a wide range of popular first-order methods, including dual averaging, dual extrapola ...

2021

Scalable Learning-Based Sampling Optimization For Compressive Dynamic MRI

Volkan Cevher, Ruud van Heeswijk, Baran Gözcü, Armin Eftekhari, Thomas Sanchez

Compressed sensing applied to magnetic resonance imaging (MRI) allows to reduce the scanning time by enabling images to be reconstructed from highly undersampled data. In this paper, we tackle the problem of designing a sampling mask for an arbitrary recon ...

IEEE2020

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

Active Learning of Multi-Index Function Models

Volkan Cevher, Hemant Tyagi

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

Generalization of Noisy SGD in Unbounded Non-convex Settings

Volkan Cevher, Leello Tadesse Dadi

We study the generalization of iterative noisy gradient schemes on smooth non-convex losses. Formally, we establish time-independent information theoretic generalization bounds for Stochastic Gradient Langevin Dynamics (SGLD) that do not diverge as the ite ...

2025

Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization

Volkan Cevher, Alp Yurtsever, Maria-Luiza Vladarean

We propose a stochastic conditional gradient method (CGM) for minimizing convex finitesum objectives formed as a sum of smooth and non-smooth terms. Existing CGM variants for this template either suffer from slow convergence rates, or require carefully inc ...

2022

A Game Theoretic Approach to Expander-based Compressive Sensing

Volkan Cevher

We consider the following expander-based compressive sensing (e-CS) problem: Given Φ ∈ ℝM×N (M

IEEE2011

Random extrapolation for primal-dual coordinate descent

Volkan Cevher, Ahmet Alacaoglu

We introduce a randomly extrapolated primal-dual coordinate descent method that adapts to sparsity of the data matrix and the favorable structures of the objective function. Our method updates only a subset of primal and dual variables with sparse data, an ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2020

Composite convex minimization involving self-concordant-like cost functions

Volkan Cevher, Quoc Tran Dinh, Yen-Huan Li

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

Active Learning of Self-concordant like Multi-index Functions

Volkan Cevher, Jonathan Mark Scarlett, Ilija Bogunovic

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

Best of Both Worlds: Regret Minimization versus Minimax Play

Volkan Cevher, Luca Viano

In this paper, we investigate the existence of online learning algorithms with bandit feedback that simultaneously guarantee O(1) regret compared to a given comparator strategy, and Õ(√ T) regret compared to any fixed strategy, where T is the number of rou ...

2025