Home

Person

Volkan Cevher

About
Privacy
Disclaimer

Graph Chatbot

Related publications (249)

Adversarial Training Should Be Cast As a Non-Zero-Sum Game

Seyed Hamed Hassani, Volkan Cevher, Fabian Ricardo Latorre Gomez

One prominent approach toward resolving the adversarial vulnerability of deep neural networks is the two-player zero-sum paradigm of adversarial training, in which predictors are trained against adversarially-chosen perturbations of data. Despite the promi ...

2023

Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling

Volkan Cevher, Zhenyu Zhu

This paper provides statistical sample complexity bounds for score-matching and its applications in causal discovery. We demonstrate that accurate estimation of the score function is achievable by training a standard deep ReLU neural network using stochast ...

2023

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

Reza Shokri, Volkan Cevher, Zhenyu Zhu, Fanghui Liu

We analytically investigate how over-parameterization of models in randomized machine learning algorithms impacts the information leakage about their training data. Specifically, we prove a privacy bound for the KL divergence between model distributions on ...

2023

Stable Nonconvex-Nonconcave Training via Linear Interpolation

Volkan Cevher, Thomas Michaelsen Pethick, Wanyun Xie

This paper presents a theoretical analysis of linear interpolation as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss lan ...

2023

What can online reinforcement learning with function approximation benefitfrom general coverage conditions

Volkan Cevher, Luca Viano, Fanghui Liu

2023

On the Convergence of Encoder-only Shallow Transformers

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Yongtao Wu

In this paper, we aim to build the global convergence theory of encoder-only shallow Transformers under a realistic setting from the perspective of architectures, initialization, and scaling under a finite width regime. The difficulty lies in how to tackle ...

2023

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

Benign Overfitting in Deep Neural Networks under Lazy Training

Volkan Cevher, Zhenyu Zhu, Grigorios Chrysos, Fanghui Liu

This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayesoptimal test error for classification while obtaining (nearly) zero-trai ...

2023

Regularization of polynomial networks for image recognition

Volkan Cevher, Bohan Wang, Grigorios Chrysos

Deep Neural Networks (DNNs) have obtained impressive performance across tasks, however they still remain as black boxes, e.g., hard to theoretically analyze. At the same time, Polynomial Networks (PNs) have emerged as an alternative method with a promising ...

Ieee Computer Soc2023

Efficient Online Clustering with Moving Costs

Volkan Cevher, Efstratios Panteleimon Skoulakis

In this work we consider an online learning problem, called Online k-Clustering with Moving Costs, at which a learner maintains a set of k facilities over T rounds so as to minimize the connection cost of an adversarially selected sequence of clients. The ...

2023

Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees

Volkan Cevher, Luca Viano, Efstratios Panteleimon Skoulakis

In this work, we introduce a new variant of online gradient descent, which provably converges to Nash Equilibria and simultaneously attains sublinear regret for the class of congestion games in the semi-bandit feedback setting. Our proposed method admits c ...

2023

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Volkan Cevher, Zhenyu Zhu, Grigorios Chrysos, Fanghui Liu, Yongtao Wu

Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural networks and their generalization bounds. The study on NTK has been devoted to typical neural network architectures, but it is incomplete for neural networks with Hadamar ...

2022

Sound and Complete Verification of Polynomial Networks

Volkan Cevher, Mehmet Fatih Sahin, Grigorios Chrysos, Fanghui Liu, Elias Abad Rocamora

Polynomial Networks (PNs) have demonstrated promising performance on face and image recognition recently. However, robustness of PNs is unclear and thus obtaining certificates becomes imperative for enabling their adoption in real-world applications. Exist ...

2022

A Natural Actor-Critic Framework for Zero-Sum Markov Games

Volkan Cevher, Luca Viano

We introduce algorithms based on natural actorcritic and analyze their sample complexity for solving two player zero-sum Markov games in the tabular case. Our results improve the best-known sample complexities of policy gradient/actorcritic methods for con ...

PMLR2022

UNDERGRAD: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees

Volkan Cevher, Kimon Antonakopoulos

Universal methods for optimization are designed to achieve theoretically optimal convergence rates without any prior knowledge of the problem’s regularity parameters or the accurarcy of the gradient oracle employed by the optimizer. In this regard, existin ...

2022

The spectral bias of polynomial neural networks

Volkan Cevher, Moulik Choraria, Leello Tadesse Dadi, Grigorios Chrysos

Polynomial neural networks (PNNs) have been recently shown to be particularly effective at image generation and face recognition, where high-frequency information is critical. Previous studies have revealed that neural networks demonstrate a spectral bias ...

2022

High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize

Volkan Cevher, Ali Kavis

In this paper, we propose a new, simplified high probability analysis of AdaGrad for smooth, non-convex problems. More specifically, we focus on a particular accelerated gradient (AGD) template (Lan, 2020) through which we recover the original AdaGrad and ...

2022

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

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

Next generation invasive neural interfaces require fully implantable wireless systems that can record from a large number of channels simultaneously. However, transferring the recorded data from the implant to an external receiver emerges as a significant ...

2022

Controlling the Complexity and Lipschitz Constant improves Polynomial Nets

Volkan Cevher, Fabian Ricardo Latorre Gomez, Zhenyu Zhu, Grigorios Chrysos

While the class of Polynomial Nets demonstrates comparable performance to neural networks (NN), it currently has neither theoretical generalization characterization nor robustness guarantees. To this end, we derive new complexity bounds for the set of Coup ...

2022

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

Page 3 of 13