Recherche

Afficher tous les résultats pour

Accueil

Personne

Volkan Cevher

À propos
Confidentialité
Mentions légales

Graph Chatbot

Publications associées (249)

Page 3 sur 13

Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach

Volkan Cevher, Slobodan Mitrovic, Ilija Bogunovic, Jakub Tarnawski, Ashkan Norouzi Fard

We study the classical problem of maximizing a monotone submodular function subject to a cardinality constraint k, with two additional twists: (i) elements arrive in a streaming fashion and (ii) m items from the algorithm’s memory might be removed after th ...

2017

Stochastic Frank-Wolfe for Composite Convex Minimization

Volkan Cevher, Alp Yurtsever

A broad class of convex optimization problems can be formulated as a semidefinite program (SDP), minimization of a convex function over the positive-semidefinite cone subject to some affine constraints. The majority of classical SDP solvers are designed fo ...

2019

Adversarial Training For Defense Against Label Poisoning Attacks

Volkan Cevher

As machine learning models grow in complexity and increasingly rely on publicly sourced data, such as the human-annotated labels used in training large language models, they become more vulnerable to label poisoning attacks. These attacks, in which adversa ...

2025

Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization

Volkan Cevher, Jonathan Mark Scarlett, Ilija Bogunovic

In this paper, we consider the problem of sequentially optimizing a black-box function

f

based on noisy samples and bandit feedback. We assume that

f

is smooth in the sense of having a bounded norm in some reproducing kernel Hilbert space (RKHS), yield ...

2017

Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

Volkan Cevher, Ali Kavis, Kimon Antonakopoulos, Leello Tadesse Dadi, Efstratios Panteleimon Skoulakis

We propose an adaptive variance-reduction method, called AdaSpider, for minimization of L-smooth, non-convex functions with a finite-sum structure. In essence, AdaSpider combines an AdaGrad-inspired [Duchi et al., 2011, McMahan & Streeter, 2010], but a fai ...

2022

Near-Optimal Noisy Group Testing via Separate Decoding of Items

Volkan Cevher, Jonathan Mark Scarlett

The group testing problem consists of determining a small set of defective items from a larger set of items based on a number of tests, and is relevant in applications such as medical testing, communication protocols, pattern matching, and more. In this pa ...

2018

On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems

Volkan Cevher, Ali Kavis, Shaul Nadav Hallak

This paper analyzes the trajectories of stochastic gradient descent (SGD) to help understand the algorithm’s convergence properties in non-convex problems. We first show that the sequence of iterates generated by SGD remains bounded and converges with prob ...

2020

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

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

Structured Sparsity Models for Reverberant Speech Separation

Volkan Cevher, Hervé Bourlard, Afsaneh Asaei, Mohammad Golbabaee

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

Efficient Proximal Mapping of the 1-path-norm of Shallow Networks

Volkan Cevher, Fabian Ricardo Latorre Gomez, Paul Thierry Yves Rolland, Shaul Nadav Hallak

We demonstrate two new important properties of the 1-path-norm of shallow neural networks. First, despite its non-smoothness and non-convexity it allows a closed form proximal operator which can be efficiently computed, allowing the use of stochastic proxi ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2020

A Conditional Gradient-Based Augmented Lagrangian Framework

Volkan Cevher, Alp Yurtsever

This paper considers a generic convex minimization template with affine constraints over a compact domain, which covers key semidefinite programming applications. The existing conditional gradient methods either do not apply to our template or are too slow ...

2019

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations

Volkan Cevher, Grigorios Chrysos, Igor Krawczuk, Justin Samuel Deschenaux

Denoising Diffusion Probabilistic Models (DDPMs) exhibit remarkable capabilities in image generation, with studies suggesting that they can generalize by composing latent factors learned from the training data. In this work, we go further and study DDPMs t ...

2024

Finding Actual Descent Directions For Adversarial Training

Volkan Cevher, Fabian Ricardo Latorre Gomez, Igor Krawczuk, Thomas Michaelsen Pethick, Leello Tadesse Dadi

Adversarial Training using a strong first-order adversary (PGD) is the gold standard for training Deep Neural Networks that are robust to adversarial examples. We show that, contrary to the general understanding of the method, the gradient at an optimal ad ...

2023

A Primal-dual Framework For Mixtures Of Regularisers

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

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

Mirrored Langevin Dynamics

Volkan Cevher, Ya-Ping Hsieh, Ali Kavis, Paul Thierry Yves Rolland

We consider the problem of sampling from constrained distributions, which has posed significant challenges to both non-asymptotic analysis and algorithmic design. We propose a unified framework, which is inspired by the classical mirror descent, to derive ...

2018

Learning Ridge Functions With Randomized Sampling In High Dimensions

Volkan Cevher, Hemant Tyagi

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

Robust Maximization of Non-Submodular Objectives

Volkan Cevher, Ilija Bogunovic

We study the problem of maximizing a monotone set function subject to a cardinality constraint k in the setting where some number of elements is deleted from the returned set. The focus of this work is on the worst-case adversarial setting. While there exi ...

2018

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Volkan Cevher, Fanghui Liu

This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate shifts. By a bias-variance decomposi ...

2024

Learning Data Triage: Linear Decoding Works for Compressive MRI

Volkan Cevher, Yen-Huan Li

The standard approach to compressive sampling considers recovering an unknown deterministic signal with certain known structure, and designing the sub-sampling pattern and recovery algorithm based on the known structure. This approach requires looking for ...

Ieee2016

An area and power efficient on-the-fly LBCS transformation for implantable neuronal signal acquisition systems

Yusuf Leblebici, Volkan Cevher, Luca Baldassarre, Cosimo Aprile

A power and area effcient hardware encoding system tailored for wireless implantable applications is presented. Constant medical monitoring allowed by implantable devices is the most relevant alternative to current bulky monitoring systems, which, in case ...

2018