Ayfer Ozgur
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ayfer Ozgur has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Xiugang Wu
University of Delaware
5 shared publications Yikun Bai
Department of Electrical and Computer Engineering, University of Delaware, Newark, DE, USA
3 shared publications- Daria Reshetova
Department of Electrical Engineering, Stanford University, Stanford, CA, USA
2 shared publications - Wei-Ning Chen
Department of Electrical Engineering, Stanford University, Stanford, CA, USA
2 shared publications - Ashish Khisti
University of Toronto
1 shared publication - Cem Kalkanlı
Department of Electrical Engineering, Stanford University, Stanford, CA, USA
1 shared publication
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 72 (11) , 8955-8968
The Performance of Compression-Based Denoisers
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 72 (11) , 8955-8968
The Performance of Compression-Based Denoisers
- 15 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 43 (7) , 2333-2348
Information Compression in the AI Era: Recent Advances and Future Challenges
This survey article focuses on the emerging connections between machine learning and data compression. While the fundamental limits of classical (lossy) data compression are well-established through rate-distortion theory, recent advancements have uncovered new theoretical analyses and application areas inspired by machine learning. We review recent works on task-based and goal-oriented compression, rate-distortion-perception theory, and compression for estimation and inference. Deep learning-based approaches have provided natural, data-driven methods for compression. Accordingly, we survey recent efforts in applying deep learning techniques to task-based or goal-oriented compression, as well as image/video compression and transmission. Additionally, we discuss the potential use of large language models for text compression. Finally, we outline future research directions in this promising field.
- 15 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 43 (7) , 2333-2348
Information Compression in the AI Era: Recent Advances and Future Challenges
This survey article focuses on the emerging connections between machine learning and data compression. While the fundamental limits of classical (lossy) data compression are well-established through rate-distortion theory, recent advancements have uncovered new theoretical analyses and application areas inspired by machine learning. We review recent works on task-based and goal-oriented compression, rate-distortion-perception theory, and compression for estimation and inference. Deep learning-based approaches have provided natural, data-driven methods for compression. Accordingly, we survey recent efforts in applying deep learning techniques to task-based or goal-oriented compression, as well as image/video compression and transmission. Additionally, we discuss the potential use of large language models for text compression. Finally, we outline future research directions in this promising field.
- 16 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 5, 221-235
Training Generative Models From Privatized Data via Entropic Optimal Transport
Local differential privacy is a powerful method for privacy-preserving data collection. In this paper, we develop a framework for training Generative Adversarial Networks (GANs) on differentially privatized data. We show that entropic regularization of optimal transport – a popular regularization method in the literature that has often been leveraged for its computational benefits – enables the generator to learn the raw (unprivatized) data distribution even though it only has access to privatized samples. We prove that at the same time this leads to fast statistical convergence at the parametric rate. This shows that entropic regularization of optimal transport uniquely enables the mitigation of both the effects of privatization noise and the curse of dimensionality in statistical convergence. We provide experimental evidence to support the efficacy of our framework in practice.
- 16 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 5, 221-235
Training Generative Models From Privatized Data via Entropic Optimal Transport
Local differential privacy is a powerful method for privacy-preserving data collection. In this paper, we develop a framework for training Generative Adversarial Networks (GANs) on differentially privatized data. We show that entropic regularization of optimal transport – a popular regularization method in the literature that has often been leveraged for its computational benefits – enables the generator to learn the raw (unprivatized) data distribution even though it only has access to privatized samples. We prove that at the same time this leads to fast statistical convergence at the parametric rate. This shows that entropic regularization of optimal transport uniquely enables the mitigation of both the effects of privatization noise and the curse of dimensionality in statistical convergence. We provide experimental evidence to support the efficacy of our framework in practice.
- 9 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 69 (9) , 5956-5970
Asymptotic Performance of Thompson Sampling for Batched Multi-Armed Bandits
We study the asymptotic performance of the Thompson sampling algorithm in the batched multi-armed bandit setting where the time horizon $T$ is divided into batches, and the agent is not able to observe the rewards of her actions until the end of each batch. We show that in this batched setting, Thompson sampling achieves the same asymptotic performance as in the case where instantaneous feedback is available after each action, provided that the batch sizes increase subexponentially. This result implies that Thompson sampling can maintain its performance even if it receives delayed feedback in $\omega (\log T)$ batches. We further propose an adaptive batching scheme that reduces the number of batches to $O(\log \log T)$ while maintaining the same performance. Although the batched multi-armed bandit setting has been considered in several recent works, previous results rely on tailored algorithms for the batched setting, which optimize the batch structure and prioritize exploration in the beginning of the experiment to eliminate suboptimal actions. We show that Thompson sampling, on the other hand, is able to achieve a similar asymptotic performance in the batched setting without any modifications.
- 9 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 69 (9) , 5956-5970
Asymptotic Performance of Thompson Sampling for Batched Multi-Armed Bandits
We study the asymptotic performance of the Thompson sampling algorithm in the batched multi-armed bandit setting where the time horizon $T$ is divided into batches, and the agent is not able to observe the rewards of her actions until the end of each batch. We show that in this batched setting, Thompson sampling achieves the same asymptotic performance as in the case where instantaneous feedback is available after each action, provided that the batch sizes increase subexponentially. This result implies that Thompson sampling can maintain its performance even if it receives delayed feedback in $\omega (\log T)$ batches. We further propose an adaptive batching scheme that reduces the number of batches to $O(\log \log T)$ while maintaining the same performance. Although the batched multi-armed bandit setting has been considered in several recent works, previous results rely on tailored algorithms for the batched setting, which optimize the batch structure and prioritize exploration in the beginning of the experiment to eliminate suboptimal actions. We show that Thompson sampling, on the other hand, is able to achieve a similar asymptotic performance in the batched setting without any modifications.
- 22 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 69 (7) , 4758-4776
Adaptive Group Testing on Networks With Community Structure: The Stochastic Block Model
Group testing was conceived during World War II to identify soldiers infected with syphilis using as few tests as possible, and it has attracted renewed interest during the COVID-19 pandemic. A long-standing assumption in the probabilistic variant of the group testing problem is that individuals are infected by the disease independently . However, this assumption rarely holds in practice, as diseases often spread through interactions between individuals and therefore cause infections to be correlated. Inspired by characteristics of COVID-19 and other infectious diseases, we introduce an infection model over networks which generalizes the traditional i.i.d. model from probabilistic group testing. Under this model, we ask whether knowledge of the network structure can be leveraged to perform group testing more efficiently, focusing specifically on community-structured graphs drawn from the stochastic block model. We prove that a simple community-aware algorithm outperforms the baseline binary splitting algorithm when the model parameters are conducive to “strong community structure.” Moreover, our novel lower bounds imply that the community-aware algorithm is order-optimal in certain parameter regimes. We extend our bounds to the noisy setting and support our results with numerical experiments.
- 22 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 69 (7) , 4758-4776
Adaptive Group Testing on Networks With Community Structure: The Stochastic Block Model
Group testing was conceived during World War II to identify soldiers infected with syphilis using as few tests as possible, and it has attracted renewed interest during the COVID-19 pandemic. A long-standing assumption in the probabilistic variant of the group testing problem is that individuals are infected by the disease independently . However, this assumption rarely holds in practice, as diseases often spread through interactions between individuals and therefore cause infections to be correlated. Inspired by characteristics of COVID-19 and other infectious diseases, we introduce an infection model over networks which generalizes the traditional i.i.d. model from probabilistic group testing. Under this model, we ask whether knowledge of the network structure can be leveraged to perform group testing more efficiently, focusing specifically on community-structured graphs drawn from the stochastic block model. We prove that a simple community-aware algorithm outperforms the baseline binary splitting algorithm when the model parameters are conducive to “strong community structure.” Moreover, our novel lower bounds imply that the community-aware algorithm is order-optimal in certain parameter regimes. We extend our bounds to the noisy setting and support our results with numerical experiments.
- 16 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 69 (4) , 2059-2073
Information Constrained Optimal Transport: From Talagrand, to Marton, to Cover
The optimal transport problem studies how to transport one measure to another in the most cost-effective way and has wide range of applications from economics to machine learning. In this paper, we introduce and study an information constrained variation of this problem. Our study yields a strengthening and generalization of Talagrand’s celebrated transportation cost inequality. Following Marton’s approach, we show that the new transportation cost inequality can be used to recover old and new concentration of measure results. Finally, we provide an application of this new inequality to network information theory. We show that it can be used to recover almost immediately a recent solution to a long-standing open problem posed by Cover regarding the capacity of the relay channel.
- 16 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 69 (4) , 2059-2073
Information Constrained Optimal Transport: From Talagrand, to Marton, to Cover
The optimal transport problem studies how to transport one measure to another in the most cost-effective way and has wide range of applications from economics to machine learning. In this paper, we introduce and study an information constrained variation of this problem. Our study yields a strengthening and generalization of Talagrand’s celebrated transportation cost inequality. Following Marton’s approach, we show that the new transportation cost inequality can be used to recover old and new concentration of measure results. Finally, we provide an application of this new inequality to network information theory. We show that it can be used to recover almost immediately a recent solution to a long-standing open problem posed by Cover regarding the capacity of the relay channel.
- Open Access
Understanding Entropic Regularization in GANs
Generative Adversarial Networks are a popular method for learning distributions from data by modeling the target distribution as a function of a known distribution. The function, often referred to as the generator, is optimized to minimize a chosen distance measure between the generated and target distributions. One commonly used measure for this purpose is the Wasserstein distance. However, Wasserstein distance is hard to compute and optimize, and in practice entropic regularization techniques are used to improve numerical convergence. The influence of regularization on the learned solution, however, remains not well-understood. In this paper, we study how several popular entropic regularizations of Wasserstein distance impact the solution in a simple benchmark setting where the generator is linear and the target distribution is high-dimensional Gaussian. We show that entropy regularization promotes the solution sparsification, while replacing the Wasserstein distance with the Sinkhorn divergence recovers the unregularized solution. Both regularization techniques remove the curse of dimensionality suffered by Wasserstein distance. We show that the optimal generator can be learned to accuracy $\epsilon$ with $O(1/\epsilon^2)$ samples from the target distribution. We thus conclude that these regularization techniques can improve the quality of the generator learned from empirical data for a large class of distributions.Open AccessUnderstanding Entropic Regularization in GANs
Generative Adversarial Networks are a popular method for learning distributions from data by modeling the target distribution as a function of a known distribution. The function, often referred to as the generator, is optimized to minimize a chosen distance measure between the generated and target distributions. One commonly used measure for this purpose is the Wasserstein distance. However, Wasserstein distance is hard to compute and optimize, and in practice entropic regularization techniques are used to improve numerical convergence. The influence of regularization on the learned solution, however, remains not well-understood. In this paper, we study how several popular entropic regularizations of Wasserstein distance impact the solution in a simple benchmark setting where the generator is linear and the target distribution is high-dimensional Gaussian. We show that entropy regularization promotes the solution sparsification, while replacing the Wasserstein distance with the Sinkhorn divergence recovers the unregularized solution. Both regularization techniques remove the curse of dimensionality suffered by Wasserstein distance. We show that the optimal generator can be learned to accuracy $\epsilon$ with $O(1/\epsilon^2)$ samples from the target distribution. We thus conclude that these regularization techniques can improve the quality of the generator learned from empirical data for a large class of distributions. - Open Access
- 15 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 39 (8) , 2267-2270
Series Editorial: The Third Issue of the Series on Machine Learning in Communications and Networks
The Second Call for Papers of the Series on Machine Learning in Communications and Networks has continued to receive a great number of high-quality papers covering various aspects of intelligent communication systems. In addition to those already published, we include in this issue 27 articles that have been submitted to the call. In the following, we provide a brief review of key contributions of papers in this issue according to their topics.
- 15 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 39 (8) , 2267-2270
Open AccessSeries Editorial: The Third Issue of the Series on Machine Learning in Communications and Networks
The Second Call for Papers of the Series on Machine Learning in Communications and Networks has continued to receive a great number of high-quality papers covering various aspects of intelligent communication systems. In addition to those already published, we include in this issue 27 articles that have been submitted to the call. In the following, we provide a brief review of key contributions of papers in this issue according to their topics.
- Open Access
Information Constrained Optimal Transport: From Talagrand, to Marton, to Cover
The optimal transport problem studies how to transport one measure to another in the most cost-effective way and has wide range of applications from economics to machine learning. In this paper, we introduce and study an information constrained variation of this problem. Our study yields a strengthening and generalization of Talagrand's celebrated transportation cost inequality. Following Marton's approach, we show that the new transportation cost inequality can be used to recover old and new concentration of measure results. Finally, we provide an application of this new inequality to network information theory. We show that it can be used to recover almost immediately a recent solution to a long-standing open problem posed by Cover regarding the capacity of the relay channel.
Open AccessInformation Constrained Optimal Transport: From Talagrand, to Marton, to Cover
The optimal transport problem studies how to transport one measure to another in the most cost-effective way and has wide range of applications from economics to machine learning. In this paper, we introduce and study an information constrained variation of this problem. Our study yields a strengthening and generalization of Talagrand's celebrated transportation cost inequality. Following Marton's approach, we show that the new transportation cost inequality can be used to recover old and new concentration of measure results. Finally, we provide an application of this new inequality to network information theory. We show that it can be used to recover almost immediately a recent solution to a long-standing open problem posed by Cover regarding the capacity of the relay channel.