Home

Person

Volkan Cevher

About
Privacy
Disclaimer

Graph Chatbot

Related publications (249)

Page 5 of 13

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

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

Overlapping Multi-Bandit Best Arm Identification

Volkan Cevher, Jonathan Mark Scarlett, Ilija Bogunovic

In the multi-armed bandit literature, the multi-bandit best-arm identification problem consists of determining each best arm in a number of disjoint groups of arms, with as few total arm pulls as possible. In this paper, we introduce a variant of the multi ...

IEEE2019

Real-time DCT Learning-based Reconstruction of Neural Signals

Volkan Cevher, Cosimo Aprile, Rabeeh Karimi Mahabadi

Wearable and implantable body sensor network systems are one of the key technologies for continuous monitoring of patient’s vital health status such as temperature and blood pressure, and brain activity. Such devices are critical for early detection of eme ...

IEEE2018

Adaptive Learning-Based Compressive Sampling for Low-power Wireless Implants

Yusuf Leblebici, Volkan Cevher, Catherine Dehollain, Mahsa Shoaran, Luca Baldassarre, Franco Maloberti, Cosimo Aprile, Kerim Türe, Gürkan Yilmaz

Implantable systems are nowadays being used to interface the human brain with external devices, in order to understand and potentially treat neurological disorders. The most predominant design constraints are the system’s area and power. In this paper, we ...

2018

A 16-Channel Wireless Neural Recording System-on-Chip with CHT Feature Extraction Processor in 65nm CMOS

Yusuf Leblebici, Volkan Cevher, Stéphanie Lacour, Catherine Dehollain, Florian Dylan Fallegger, Cosimo Aprile, Kerim Türe, Alix Esther Anne Trouillet, Arda Uran

Wireless implantable neural recording chips enable multichannel data acquisition with high spatiotemporal resolution in situ. Recently, the use of machine learning approaches on neural data for diagnosis and prosthesis control have renewed the interest in ...

2021

STORM+: Fully Adaptive SGD with Momentum for Nonconvex Optimization

Volkan Cevher, Ali Kavis

In this work we investigate stochastic non-convex optimization problems wherethe objective is an expectation over smooth loss functions, and the goal is to find an approximate stationary point. The most popular approach to handling such problems is varianc ...

2021

Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems

Volkan Cevher, Thomas Michaelsen Pethick

This paper introduces a new extragradient-type algorithm for a class of nonconvex-nonconcave minimax problems. It is well-known that finding a local solution for general minimax problems is computationally intractable. This observation has recently motivat ...

2022

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

Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods

Volkan Cevher, Junhong Lin

We study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We investigate distributed stochastic gradient methods (SGM), with mini-batches and multi-passes over th ...

2018

Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator

Volkan Cevher, Alp Yurtsever

We propose a class of novel variance-reduced stochastic conditional gradient methods. By adopting the recent stochastic path-integrated differential estimator technique (SPIDER) of Fang et al. (2018) for the classical Frank-Wolfe (FW) method, we introduce ...

2019

A Newton Frank-Wolfe method for constrained self-concordant minimization

Volkan Cevher, Quoc Tran Dinh

We develop a new Newton Frank-Wolfe algorithm to solve a class of constrained self-concordant minimization problems using linear minimization oracles (LMO). Unlike L-smooth convex functions, where the Lipschitz continuity of the objective gradient holds gl ...

SPRINGER2022

On the Generalization of Stochastic Gradient Descent with Momentum

Volkan Cevher, Kimon Antonakopoulos

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

Microtome Publishing2024

An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints

Volkan Cevher, Ahmet Alacaoglu, Fabian Ricardo Latorre Gomez, Armin Eftekhari, Mehmet Fatih Sahin

We propose a practical inexact augmented Lagrangian method (iALM) for nonconvex problems with nonlinear constraints. We characterize the total computational complexity of our method subject to a verifiable geometric condition, which is closely related to t ...

2019

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

Volkan Cevher, Jonathan Mark Scarlett, Yen-Huan Li

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

Subquadratic Overparameterization for Shallow Neural Networks

Chaehwan Song, Volkan Cevher, Armin Eftekhari, Thomas Michaelsen Pethick

Overparameterization refers to the important phenomenon where the width of a neural network is chosen such that learning algorithms can provably attain zero loss in nonconvex training. The existing theory establishes such global convergence using various i ...

2021

Maximum Independent Set: Self-Training through Dynamic Programming

Volkan Cevher, Grigorios Chrysos, Efstratios Panteleimon Skoulakis

This work presents a graph neural network (GNN) framework for solving the maximum independent set (MIS) problem, inspired by dynamic programming (DP). Specifically, given a graph, we propose a DP-like recursive algorithm based on GNNs that firstly construc ...

2023

Rethinking Sampling in Parallel MRI: A Data-Driven Approach

Volkan Cevher, Baran Gözcü, Thomas Sanchez

In the last decade, Compressive Sensing (CS) has emerged as the most promising, model-driven approach to accelerate MRI scans. CS relies on the key sparsity assumption and proposes random sampling for data acquisition. The practical CS approaches in MRI em ...

IEEE2019

Scalable sparse covariance estimation via self-concordance

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

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

Learning to Remove Cuts in Integer Linear Programming

Volkan Cevher, Grigorios Chrysos, Efstratios Panteleimon Skoulakis

Cutting plane methods are a fundamental approach for solving integer linear programs (ILPs). In each iteration of such methods, additional linear constraints (cuts) are introduced to the constraint set with the aim of excluding the previous fractional opti ...

2024