Recherche

Afficher tous les résultats pour

Accueil

Personne

Volkan Cevher

À propos
Confidentialité
Mentions légales

Graph Chatbot

Publications associées (249)

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

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

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

Kernel Conjugate Gradient Methods with Random Projections

Volkan Cevher, Junhong Lin

We propose and study kernel conjugate gradient methods (KCGM) with random projections for least-squares regression over a separable Hilbert space. Considering two types of random projections generated by randomized sketches and Nyström subsampling, we prov ...

2021

A Plug-and-Play Deep Image Prior

Volkan Cevher, Thomas Sanchez, Fabian Ricardo Latorre Gomez, Zhaodong Sun

Deep image priors (DIP) offer a novel approach for the regularization that leverages the inductive bias of a deep convolutional architecture in inverse problems. However, the quality of DIP approaches often degrades when the number of iterations exceeds a ...

IEEE2021

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

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

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

Forward-reflected-backward method with variance reduction

Volkan Cevher, Ahmet Alacaoglu

We propose a variance reduced algorithm for solving monotone variational inequalities. Without assuming strong monotonicity, cocoercivity, or boundedness of the domain, we prove almost sure convergence of the iterates generated by the algorithm to a soluti ...

2021

An Introductory Guide to Fano's Inequality with Applications in Statistical Estimation

Volkan Cevher, Jonathan Mark Scarlett

Information theory plays an indispensable role in the development of algorithm-independent impossibility results, both for communication problems and for seemingly distinct areas such as statistics and machine learning. While numerous information-theoretic ...

Cambridge University Press2021

Asynchronous sar adc with unit length capacitors and constant common mode monotonic switching

Volkan Cevher, Arda Uran

A Successive Approximation Register Analog-to-Digital Converter (SAR ADC) comprising a Track-and-Hold (T/H) switch configured for a sampling of an input voltage in the form of charge onto a capacitor; a Capacitive Digital-to- Analog Converter (CD AC) opera ...

2021

Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach

Volkan Cevher, Shaul Nadav Hallak

This paper develops a methodology for regret minimization with stochastic first-order oracle feedback in online, constrained, non-smooth, non-convex problems. In this setting, the minimization of external regret is beyond reach for first-order methods, and ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2021

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

Double-Loop Unadjusted Langevin Algorithm

Armin Eftekhari, Volkan Cevher, Paul Thierry Yves Rolland, Ali Kavis

A well-known first-order method for sampling from log-concave probability distributions is the Unadjusted Langevin Algorithm (ULA). This work proposes a new annealing step-size schedule for ULA, which allows to prove new convergence guarantees for sampling ...

2020

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

Volkan Cevher, Paul Thierry Yves Rolland, Fabian Ricardo Latorre Gomez, 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

Optimization for Reinforcement Learning: From a single agent to cooperative agents

Volkan Cevher, Kamalaruban Parameswaran

Fueled by recent advances in deep neural networks, reinforcement learning (RL) has been in the limelight because of many recent breakthroughs in artificial intelligence, including defeating humans in games (e.g., chess, Go, StarCraft), self-driving cars, s ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

Machine Learning From Distributed, Streaming Data [From the Guest Editors]

Volkan Cevher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

An AC-Coupled Wideband Neural Recording Front-End With Sub-1 mm2×fJ/conv-step Efficiency and 0.97 NEF

Yusuf Leblebici, Volkan Cevher, Arda Uran

This letter presents an energy-and-area-efficient ac-coupled front-end for the multichannel recording of wideband neural signals. The proposed unit conditions local held and action potentials using an inverter-based capacitively coupled low-noise amplifier ...

2020

Convergences of Regularized Algorithms and Stochastic Gradient Methods with Random Projections

Volkan Cevher, Junhong Lin

We study the least-squares regression problem over a Hilbert space, covering nonparametric regression over a reproducing kernel Hilbert space as a special case. We rst investigate regularized algorithms adapted to a projection operator on a closed subspace ...

2020

Lipschitz constant estimation for Neural Networks via sparse polynomial optimization

Volkan Cevher, Paul Thierry Yves Rolland, Fabian Ricardo Latorre Gomez

We introduce LiPopt, a polynomial optimization framework for computing increasingly tighter upper bounds on the Lipschitz constant of neural networks. The underlying optimization problems boil down to either linear (LP) or semidefinite (SDP) programming. W ...

2020

Optimal Rates for Spectral Algorithms with Least-Squares Regression over Hilbert Spaces

Volkan Cevher, Junhong Lin

In this paper, we study regression problems over a separable Hilbert space with the square loss, covering non-parametric regression over a reproducing kernel Hilbert space. We investigate a class of spectral/regularized algorithms, including ridge regressi ...

2020

A new regret analysis for Adam-type algorithms

Volkan Cevher, Ahmet Alacaoglu

In this paper, we focus on a theory-practice gap for Adam and its variants (AMSgrad, AdamNC, etc.). In practice, these algorithms are used with a constant first-order moment parameter 1 (typically between 0:9 and 0:99). In theory, regret guarantees for onl ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2020

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

Conditional gradient methods for stochastically constrained convex minimization

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

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

Page 5 sur 13