Nuri Denizcan Vanli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Nuri Denizcan Vanli has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Suleyman Serdar Kozat
Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Trkiye
6 shared publications - Muhammed Omer Sayin
Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Trkiye
4 shared publications - Asuman Ozdaglar
EECS LIDS Massachusetts Institute of Technology
3 shared publications - Huseyin Ozkan
Sabanci University
2 shared publications - Mert Gurbuzbalaban
Department of Management Science and Information Systems, Rutgers Business School, Piscataway, New Jersey 08854
2 shared publications - Stephen J. Wright
University of Wisconsin-Madison
2 shared publications
Latest Publications
- 30 July 2021
- Published by Springer Nature in Mathematical Programming
- Vol. 195 (1-2) , 243-281
Convergence rate of block-coordinate maximization Burer–Monteiro method for solving large SDPs
- 30 July 2021
- Published by Springer Nature in Mathematical Programming
- Vol. 195 (1-2) , 243-281
Convergence rate of block-coordinate maximization Burer–Monteiro method for solving large SDPs
- 30 September 2019
- Published by Springer Nature in Mathematical Programming
- Vol. 181 (2) , 349-376
Randomness and permutations in coordinate descent methods
- 30 September 2019
- Published by Springer Nature in Mathematical Programming
- Vol. 181 (2) , 349-376
Randomness and permutations in coordinate descent methods
- 28 August 2018
- Published by Elsevier in Pattern Recognition
- Vol. 86, 1-13
Nonlinear regression via incremental decision trees
- 28 August 2018
- Published by Elsevier in Pattern Recognition
- Vol. 86, 1-13
Nonlinear regression via incremental decision trees
- Open Access
Randomness and Permutations in Coordinate Descent Methods
We consider coordinate descent (CD) methods with exact line search on convex quadratic problems. Our main focus is to study the performance of the CD method that use random permutations in each epoch and compare it to the performance of the CD methods that use deterministic orders and random sampling with replacement. We focus on a class of convex quadratic problems with a diagonally dominant Hessian matrix, for which we show that using random permutations instead of random with-replacement sampling improves the performance of the CD method in the worst-case. Furthermore, we prove that as the Hessian matrix becomes more diagonally dominant, the performance improvement attained by using random permutations increases. We also show that for this problem class, using any fixed deterministic order yields a superior performance than using random permutations. We present detailed theoretical analyses with respect to three different convergence criteria that are used in the literature and support our theoretical results with numerical experiments.
Open AccessRandomness and Permutations in Coordinate Descent Methods
We consider coordinate descent (CD) methods with exact line search on convex quadratic problems. Our main focus is to study the performance of the CD method that use random permutations in each epoch and compare it to the performance of the CD methods that use deterministic orders and random sampling with replacement. We focus on a class of convex quadratic problems with a diagonally dominant Hessian matrix, for which we show that using random permutations instead of random with-replacement sampling improves the performance of the CD method in the worst-case. Furthermore, we prove that as the Hessian matrix becomes more diagonally dominant, the performance improvement attained by using random permutations increases. We also show that for this problem class, using any fixed deterministic order yields a superior performance than using random permutations. We present detailed theoretical analyses with respect to three different convergence criteria that are used in the literature and support our theoretical results with numerical experiments.
- 1 September 2017
- Published by Elsevier in Physical Communication
- Vol. 24, 83-93
Adaptive and efficient nonlinear channel equalization for underwater acoustic communication
- 1 September 2017
- Published by Elsevier in Physical Communication
- Vol. 24, 83-93
Adaptive and efficient nonlinear channel equalization for underwater acoustic communication
- Open Access
- 8 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 4 (4) , 248-260
Stochastic Subgradient Algorithms for Strongly Convex Optimization Over Distributed Networks
We study diffusion and consensus based optimization of a sum of unknown convex objective functions over distributed networks. The only access to these functions is through stochastic gradient oracles, each of which is only available at a different node; and a limited number of gradient oracle calls is allowed at each node. In this framework, we introduce a convex optimization algorithm based on stochastic subgradient descent (SSD) updates. We use a carefully designed time-dependent weighted averaging of the SSD iterates, which yields a convergence rate of$O\left(\frac{N\sqrt{N}}{(1-\sigma)T}\right)$ after$T$ gradient updates for each node on a network of$N$ nodes, where$0\leq \sigma <1$ denotes the second largest singular value of the communication matrix. This rate of convergence matches the performance lower bound up to constant terms. Similar to the SSD algorithm, the computational complexity of the proposed algorithm also scales linearly with the dimensionality of the data. Furthermore, the communication load of the proposed method is the same as the communication load of the SSD algorithm. Thus, the proposed algorithm is highly efficient in terms of complexity and communication load. We illustrate the merits of the algorithm with respect to the state-of-art methods over benchmark real life data sets.- 8 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 4 (4) , 248-260
Open AccessStochastic Subgradient Algorithms for Strongly Convex Optimization Over Distributed Networks
We study diffusion and consensus based optimization of a sum of unknown convex objective functions over distributed networks. The only access to these functions is through stochastic gradient oracles, each of which is only available at a different node; and a limited number of gradient oracle calls is allowed at each node. In this framework, we introduce a convex optimization algorithm based on stochastic subgradient descent (SSD) updates. We use a carefully designed time-dependent weighted averaging of the SSD iterates, which yields a convergence rate of$O\left(\frac{N\sqrt{N}}{(1-\sigma)T}\right)$ after$T$ gradient updates for each node on a network of$N$ nodes, where$0\leq \sigma <1$ denotes the second largest singular value of the communication matrix. This rate of convergence matches the performance lower bound up to constant terms. Similar to the SSD algorithm, the computational complexity of the proposed algorithm also scales linearly with the dimensionality of the data. Furthermore, the communication load of the proposed method is the same as the communication load of the SSD algorithm. Thus, the proposed algorithm is highly efficient in terms of complexity and communication load. We illustrate the merits of the algorithm with respect to the state-of-art methods over benchmark real life data sets. - 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2290-2294
Adaptive hierarchical space partitioning for online classification
We propose an online algorithm for supervised learning with strong performance guarantees under the empirical zero-one loss. The proposed method adaptively partitions the feature space in a hierarchical manner and generates a powerful finite combination of basic models. This provides algorithm to obtain a strong classification method which enables it to create a linear piecewise classifier model that can work well under highly non-linear complex data. The introduced algorithm also have scalable computational complexity that scales linearly with dimension of the feature space, depth of the partitioning and number of processed data. Through experiments we show that the introduced algorithm outperforms the state-of-the-art ensemble techniques over various well-known machine learning data sets.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2290-2294
Adaptive hierarchical space partitioning for online classification
We propose an online algorithm for supervised learning with strong performance guarantees under the empirical zero-one loss. The proposed method adaptively partitions the feature space in a hierarchical manner and generates a powerful finite combination of basic models. This provides algorithm to obtain a strong classification method which enables it to create a linear piecewise classifier model that can work well under highly non-linear complex data. The introduced algorithm also have scalable computational complexity that scales linearly with dimension of the feature space, depth of the partitioning and number of processed data. Through experiments we show that the introduced algorithm outperforms the state-of-the-art ensemble techniques over various well-known machine learning data sets.
- Open Access
Adaptive and Efficient Nonlinear Channel Equalization for Underwater Acoustic Communication
We investigate underwater acoustic (UWA) channel equalization and introduce hierarchical and adaptive nonlinear channel equalization algorithms that are highly efficient and provide significantly improved bit error rate (BER) performance. Due to the high complexity of nonlinear equalizers and poor performance of linear ones, to equalize highly difficult underwater acoustic channels, we employ piecewise linear equalizers. However, in order to achieve the performance of the best piecewise linear model, we use a tree structure to hierarchically partition the space of the received signal. Furthermore, the equalization algorithm should be completely adaptive, since due to the highly non-stationary nature of the underwater medium, the optimal MSE equalizer as well as the best piecewise linear equalizer changes in time. To this end, we introduce an adaptive piecewise linear equalization algorithm that not only adapts the linear equalizer at each region but also learns the complete hierarchical structure with a computational complexity only polynomial in the number of nodes of the tree. Furthermore, our algorithm is constructed to directly minimize the final squared error without introducing any ad-hoc parameters. We demonstrate the performance of our algorithms through highly realistic experiments performed on accurately simulated underwater acoustic channels.
Open AccessAdaptive and Efficient Nonlinear Channel Equalization for Underwater Acoustic Communication
We investigate underwater acoustic (UWA) channel equalization and introduce hierarchical and adaptive nonlinear channel equalization algorithms that are highly efficient and provide significantly improved bit error rate (BER) performance. Due to the high complexity of nonlinear equalizers and poor performance of linear ones, to equalize highly difficult underwater acoustic channels, we employ piecewise linear equalizers. However, in order to achieve the performance of the best piecewise linear model, we use a tree structure to hierarchically partition the space of the received signal. Furthermore, the equalization algorithm should be completely adaptive, since due to the highly non-stationary nature of the underwater medium, the optimal MSE equalizer as well as the best piecewise linear equalizer changes in time. To this end, we introduce an adaptive piecewise linear equalization algorithm that not only adapts the linear equalizer at each region but also learns the complete hierarchical structure with a computational complexity only polynomial in the number of nodes of the tree. Furthermore, our algorithm is constructed to directly minimize the final squared error without introducing any ad-hoc parameters. We demonstrate the performance of our algorithms through highly realistic experiments performed on accurately simulated underwater acoustic channels.
- Open Access
Stochastic Subgradient Algorithms for Strongly Convex Optimization over Distributed Networks
We study diffusion and consensus based optimization of a sum of unknown convex objective functions over distributed networks. The only access to these functions is through stochastic gradient oracles, each of which is only available at a different node, and a limited number of gradient oracle calls is allowed at each node. In this framework, we introduce a convex optimization algorithm based on the stochastic gradient descent (SGD) updates. Particularly, we use a carefully designed time-dependent weighted averaging of the SGD iterates, which yields a convergence rate of $O\left(\frac{N\sqrt{N}}{T}\right)$ after $T$ gradient updates for each node on a network of $N$ nodes. We then show that after $T$ gradient oracle calls, the average SGD iterate achieves a mean square deviation (MSD) of $O\left(\frac{\sqrt{N}}{T}\right)$. This rate of convergence is optimal as it matches the performance lower bound up to constant terms. Similar to the SGD algorithm, the computational complexity of the proposed algorithm also scales linearly with the dimensionality of the data. Furthermore, the communication load of the proposed method is the same as the communication load of the SGD algorithm. Thus, the proposed algorithm is highly efficient in terms of complexity and communication load. We illustrate the merits of the algorithm with respect to the state-of-art methods over benchmark real life data sets and widely studied network topologies.Open AccessStochastic Subgradient Algorithms for Strongly Convex Optimization over Distributed Networks
We study diffusion and consensus based optimization of a sum of unknown convex objective functions over distributed networks. The only access to these functions is through stochastic gradient oracles, each of which is only available at a different node, and a limited number of gradient oracle calls is allowed at each node. In this framework, we introduce a convex optimization algorithm based on the stochastic gradient descent (SGD) updates. Particularly, we use a carefully designed time-dependent weighted averaging of the SGD iterates, which yields a convergence rate of $O\left(\frac{N\sqrt{N}}{T}\right)$ after $T$ gradient updates for each node on a network of $N$ nodes. We then show that after $T$ gradient oracle calls, the average SGD iterate achieves a mean square deviation (MSD) of $O\left(\frac{\sqrt{N}}{T}\right)$. This rate of convergence is optimal as it matches the performance lower bound up to constant terms. Similar to the SGD algorithm, the computational complexity of the proposed algorithm also scales linearly with the dimensionality of the data. Furthermore, the communication load of the proposed method is the same as the communication load of the SGD algorithm. Thus, the proposed algorithm is highly efficient in terms of complexity and communication load. We illustrate the merits of the algorithm with respect to the state-of-art methods over benchmark real life data sets and widely studied network topologies. - Open Access
- 1 April 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21650608,p. 1861-1864
Competitive linear MMSE estimation under structured data uncertainties
In this paper, we consider the linear estimation problem under structured data uncertainties. A robust algorithm is presented under bounded uncertainties under the mean square error (MSE) criterion. The performance of the linear estimator is defined relative to the performance of the linear minimum MSE (MMSE) estimator tuned to the underlying unknown data uncertainties, i.e., the introduced algorithm has a competitive framework. Then, using this relative performance measure, we find the estimator that minimizes this cost for the worst-case system model. We show that finding this estimator can equivalently be cast as a semidefinite programming (SDP) problem. Numerical examples are provided to illustrate the theoretical results.
- 1 April 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21650608,p. 1861-1864
Open AccessCompetitive linear MMSE estimation under structured data uncertainties
In this paper, we consider the linear estimation problem under structured data uncertainties. A robust algorithm is presented under bounded uncertainties under the mean square error (MSE) criterion. The performance of the linear estimator is defined relative to the performance of the linear minimum MSE (MMSE) estimator tuned to the underlying unknown data uncertainties, i.e., the introduced algorithm has a competitive framework. Then, using this relative performance measure, we find the estimator that minimizes this cost for the worst-case system model. We show that finding this estimator can equivalently be cast as a semidefinite programming (SDP) problem. Numerical examples are provided to illustrate the theoretical results.