Home

Person

Volkan Cevher

About
Privacy
Disclaimer

Graph Chatbot

Related publications (249)

Understanding Deep Neural Function Approximation in Reinforcement Learning via ϵ-Greedy Exploration

This paper provides a theoretical study of deep neural function approximation in reinforcement learning (RL) with the ϵ-greedy exploration under the online setting. This problem setting is motivated by the successful deep Q-networks (DQN) framework that fa ...

2022

Proximal Point Imitation Learning

Volkan Cevher, Angeliki Kamoutsi, Igor Krawczuk, Luca Viano

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

Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization

Volkan Cevher, Alp Yurtsever, Maria-Luiza Vladarean

We propose a stochastic conditional gradient method (CGM) for minimizing convex finitesum objectives formed as a sum of smooth and non-smooth terms. Existing CGM variants for this template either suffer from slow convergence rates, or require carefully inc ...

2022

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 with convexity and linear convergenc ...

SIAM PUBLICATIONS2022

Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models

Volkan Cevher, Paul Thierry Yves Rolland

This paper demonstrates how to recover causal graphs from the score of the data distribution in non-linear additive (Gaussian) noise models. Using score matching algorithms as a building block, we show how to design a new generation of scalable causal disc ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2022

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

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

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

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

Identifiability and Generalizability from Multiple Experts in Inverse Reinforcement Learning

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

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

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

Volkan Cevher, Zhenyu Zhu, Grigorios Chrysos, Fanghui Liu

We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the under-parameterized setting, width has a negative effect while it improves ...

2022

Generalization Properties of NAS under Activation and Skip Connection Search

Volkan Cevher, Zhenyu Zhu, Grigorios Chrysos, Fanghui Liu

Neural Architecture Search (NAS) has fostered the automatic discovery of stateof- the-art neural architectures. Despite the progress achieved with NAS, so far there is little attention to theoretical guarantees on NAS. In this work, we study the generaliza ...

2022

No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation

Volkan Cevher, Ya-Ping Hsieh, Kimon Antonakopoulos

We examine the problem of regret minimization when the learner is involved in a continuous game with other optimizing agents: in this case, if all players follow a no-regret algorithm, it is possible to achieve significantly lower regret relative to fully ...

2022

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

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

Subquadratic Overparameterization for Shallow Neural Networks

Armin Eftekhari, Volkan Cevher, Chaehwan Song, 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

Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch

Volkan Cevher, Kamalaruban Parameswaran, Luca Viano, Yu-Ting Huang

We study the inverse reinforcement learning (IRL) problem under a transition dynamics mismatch between the expert and the learner. Specifically, we consider the Maximum Causal Entropy (MCE) IRL learner model and provide a tight upper bound on the learner’s ...

2021

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 ...

2021

A first-order primal-dual method with adaptivity to local smoothness

Volkan Cevher, Maria-Luiza Vladarean

We consider the problem of finding a saddle point for the convex-concave objective

\min_x \max_y f(x) + \langle Ax, y\rangle - g^*(y)

, where

f

is a convex function with locally Lipschitz gradient and

g

is convex and possibly non-smooth. We propose an ...

2021

A reflected forward-backward splitting method for monotone inclusions involving Lipschitzian operators

Volkan Cevher, Cong Bang Vu

In this paper, we propose a novel splitting method for finding a zero point of the sum of two monotone operators where one of them is Lipschizian. The weak convergence the method is proved in real Hilbert spaces. Applying the proposed method to composite m ...

2021

Scalable Semidefinite Programming

Volkan Cevher, Alp Yurtsever

Semidefinite programming (SDP) is a powerful framework from convex optimization that has striking potential for data science applications. This paper develops a provably correct algorithm for solving large SDP problems by economizing on both the storage an ...

2021

Convergence of adaptive algorithms for constrained weakly convex optimization

Volkan Cevher, Ahmet Alacaoglu, Yurii Malitskyi

We analyze the adaptive first order algorithm AMSGrad, for solving a constrained stochastic optimization problem with a weakly convex objective. We prove the

\tilde O(t^{-1/2})

rate of convergence for the squared norm of the gradient of Moreau envelope, ...

2021

Page 4 of 13