Home

Person

Volkan Cevher

About
Privacy
Disclaimer

Graph Chatbot

Related publications (249)

Page 6 of 13

An Optimal-Storage Approach to Semidefinite Programming Using Approximate Complementarity

Volkan Cevher, Alp Yurtsever

This paper develops a new storage-optimal algorithm that provably solves almost all semidefinite programs (SDPs). This method is particularly effective for weakly constrained SDPs under appropriate regularity conditions. The key idea is to formulate an app ...

SIAM Publications2021

Conditional gradient methods for stochastically constrained convex minimization

Volkan Cevher, Ya-Ping Hsieh, Ahmet Alacaoglu, Maria-Luiza Vladarean

We propose two novel conditional gradient-based methods for solving structured stochastic convex optimization problems with a large number of linear constraints. Instances of this template naturally arise from SDP-relaxations of combinatorial problems, whi ...

2020

Improving SAM Requires Rethinking its Optimization Formulation

Volkan Cevher, Kimon Antonakopoulos, Fabian Ricardo Latorre Gomez, Thomas Michaelsen Pethick, Wanyun Xie

This paper rethinks Sharpness-Aware Minimization (SAM), which is originally formulated as a zero-sum game where the weights of a network and a bounded perturbation try to minimize/maximize, respectively, the same differentiable loss. We argue that SAM shou ...

2024

Iterative Classroom Teaching

Pierre Dillenbourg, Volkan Cevher, Thibault Lucien Christian Asselborn, Shuqing Teresa Yeo, Louis Pierre Faucon, Kamalaruban Parameswaran

We consider the machine teaching problem in a classroom-like setting wherein the teacher has to deliver the same examples to a diverse group of students. Their diversity stems from differences in their initial internal states as well as their learning rate ...

ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE2019

Let’s be honest: An optimal no-regret framework for zero-sum games

Volkan Cevher, Ya-Ping Hsieh, Mehmet Fatih Sahin

We revisit the problem of solving two-player zero- sum games in the decentralized setting. We pro- pose a simple algorithmic framework that simulta- neously achieves the best rates for honest regret as well as adversarial regret, and in addition resolves t ...

2018

Fast Proximal algorithms for Self-concordant function minimization with application to sparse graph selection

Volkan Cevher, Anastasios Kyrillidis

The convex

\ell_1

-regularized

\log\det

divergence criterion has been shown to produce theoretically consistent graph learning. However, this objective function is challenging since the

\ell_1

-regularization is nonsmooth, the

\log\det

objective is n ...

2013

Method, apparatus and computer program product for determining the location of a plurality of speech sources

Volkan Cevher, Hervé Bourlard, Afsaneh Asaei

The present invention discloses a method, apparatus and computer program product for determining the location of a plurality of speech sources in an area of interest, comprising performing an algorithm on a signal issued by either one of said plurality of ...

2012

Faster Coordinate Descent via Adaptive Importance Sampling

Volkan Cevher, Martin Jaggi

Coordinate descent methods employ random partial updates of decision variables in order to solve huge-scale convex optimization problems. In this work, we introduce new adaptive rules for the random selection of their updates. By adaptive, we mean that our ...

PMLR2017

General Proximal Gradient Method: A Case for Non-Euclidean Norms

Volkan Cevher, Ya-Ping Hsieh, Marwa El Halabi, Cong Bang Vu, Van Quang Nguyen

In this paper, we consider composite convex minimization problems. We advocate the merit of considering Generalized Proximal gradient Methods (GPM) where the norm employed is not Euclidean. To that end, we show the tractability of the general proximity ope ...

2017

Signal Recovery and System Calibration from Multiple Compressive Poisson Measurements

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

Identifiability and Generalizability from Multiple Experts in Inverse Reinforcement Learning

Volkan Cevher, Luca Viano, Paul Thierry Yves Rolland, Boris Nikolov

While Reinforcement Learning (RL) aims to train an agent from a reward function in a given environment, Inverse Reinforcement Learning (IRL) seeks to recover the reward function from observing an expert’s behavior. It is well known that, in general, variou ...

2022

A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions

Volkan Cevher, Anastasios Kyrillidis, Quoc Tran Dinh

We propose an algorithmic framework for convex minimization problems of a composite function with two terms: a self-concordant function and a possibly nonsmooth regularization term. Our method is a new proximal Newton algorithm that features a local quadra ...

2013

Online Adaptive Methods, Universality and Acceleration

Volkan Cevher, Alp Yurtsever

We present a novel method for convex unconstrained optimization that, without any modifications, ensures: (i) accelerated convergence rate for smooth objectives, (ii) standard convergence rate in the general (non-smooth) setting, and (iii) standard converg ...

2018

Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization

Volkan Cevher, Quoc Tran Dinh, Ahmet Alacaoglu

We propose a new randomized coordinate descent method for a convex optimization template with broad applications. Our analysis relies on a novel combination of four ideas applied to the primal-dual gap function: smoothing, acceleration, homotopy, and coord ...

2017

On the linear convergence of the stochastic gradient method with constant step-size

Volkan Cevher, Cong Bang Vu

The strong growth condition (SGC) is known to be a sufficient condition for linear convergence of the stochastic gradient method using a constant step-size γ (SGM-CS). In this paper, we provide a necessary condition, for the linear convergence of SGM-CS, t ...

2018

Tractability of interpretability via selection of group-sparse models

Volkan Cevher, Luca Baldassarre

Group-based sparsity models are proven instrumental in linear regression problems for recovering signals from much fewer measurements than standard compressive sensing. A promise of these models is to lead to “interpretable” signals for which we identify i ...

2013

Structured Sparse Coding for Microphone Array Location Calibration

Volkan Cevher, Hervé Bourlard, Afsaneh Asaei

We address the problem of microphone location cali- bration where the sensor positions have a sparse spatial approximation on a discretized grid. We characterize the microphone signals as a sparse vector represented over a codebook of multi-channel signals ...

2012

Matrix ALPS: Accelerated Low Rank and Sparse Matrix Reconstruction

Volkan Cevher, Anastasios Kyrillidis

We propose Matrix ALPS for recovering a sparse plus low-rank decomposition of a matrix given its corrupted and incomplete linear measurements. Our approach is a first-order projected gradient method over non-convex sets, and it exploits a well-known memory ...

IEEE2012

On the convergence of stochastic primal-dual hybrid gradient

Volkan Cevher, Ahmet Alacaoglu

In this paper, we analyze the recently proposed stochastic primal-dual hybrid gradient (SPDHG) algorithm and provide new theoretical results. In particular, we prove almost sure convergence of the iterates to a solution and linear convergence with standard ...

2019

Proximal Point Imitation Learning

Volkan Cevher, Luca Viano, Igor Krawczuk

This work develops new algorithms with rigorous efficiency guarantees for infinite horizon imitation learning (IL) with linear function approximation without restrictive coherence assumptions. We begin with the minimax formulation of the problem and then o ...

2022