Baturalp Buyukates
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
Baturalp Buyukates has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Sennur Ulukus
Department of Electrical and Computer Engineering, University of Maryland, College Park, MD 20742, USA
5 shared publications Salman Avestimehr
University of Southern California
3 shared publications- Hessam Mahdavifar
Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
2 shared publications - Jinhyun So
Department of Electrical and Engineering and Computer Science, Daegu Gyeongbuk Institute of Science and Technology, Daegu, South Korea
2 shared publications - Melih Bastopcu
Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Trkiye
2 shared publications - Amir Ziashahabi
University of Southern California
1 shared publication
Latest Publications
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE BITS the Information Theory Magazine
- Vol. PP (26924080) , 1-12
Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions
The rapid advancement of large language models (LLMs) has transformed the landscape of natural language processing, enabling breakthroughs across a wide range of areas including question answering, machine translation, and text summarization. Yet, their deployment in real-world applications has raised concerns over reliability and trustworthiness, as LLMs remain prone to hallucinations that produce plausible but factually incorrect outputs. Uncertainty quantification (UQ) has emerged as a central research direction to address this issue, offering principled measures for assessing the trustworthiness of model generations. We begin by introducing the foundations of UQ, from its formal definition to the traditional distinction between epistemic and aleatoric uncertainty, and then highlight how these concepts have been adapted to the context of LLMs. Building on this, we examine the role of UQ in hallucination detection, where quantifying uncertainty provides a mechanism for identifying unreliable generations and improving reliability. We systematically categorize a wide spectrum of existing methods along multiple dimensions and present empirical results for several representative approaches. Finally, we discuss current limitations and outline promising future research directions, providing a clearer picture of the current landscape of LLM UQ for hallucination detection.
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE BITS the Information Theory Magazine
- Vol. PP (26924080) , 1-12
Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions
The rapid advancement of large language models (LLMs) has transformed the landscape of natural language processing, enabling breakthroughs across a wide range of areas including question answering, machine translation, and text summarization. Yet, their deployment in real-world applications has raised concerns over reliability and trustworthiness, as LLMs remain prone to hallucinations that produce plausible but factually incorrect outputs. Uncertainty quantification (UQ) has emerged as a central research direction to address this issue, offering principled measures for assessing the trustworthiness of model generations. We begin by introducing the foundations of UQ, from its formal definition to the traditional distinction between epistemic and aleatoric uncertainty, and then highlight how these concepts have been adapted to the context of LLMs. Building on this, we examine the role of UQ in hallucination detection, where quantifying uncertainty provides a mechanism for identifying unreliable generations and improving reliability. We systematically categorize a wide spectrum of existing methods along multiple dimensions and present empirical results for several representative approaches. Finally, we discuss current limitations and outline promising future research directions, providing a clearer picture of the current landscape of LLM UQ for hallucination detection.
- 17 January 2025
- Published by American Physical Society (APS) in Physical Review E
- Vol. 111 (1) , 015304
Renormalization group flow, optimal transport, and diffusion-based generative model
Diffusion-based generative models represent a forefront direction in generative artificial intelligence (AI) research today. Recent studies in physics have suggested that the renormalization group (RG) can be conceptualized as a diffusion process. This insight motivates us to develop a diffusion-based generative model by reversing the momentum-space RG flow. We establish a framework that interprets RG flow as optimal transport gradient flow, which minimizes a functional analogous to the Kullback-Leibler divergence, thereby bridging statistical physics and information theory. Our model applies forward and reverse diffusion processes in Fourier space, exploiting the sparse representation of natural images in this domain to efficiently separate signal from noise and manage image features across scales. By introducing a scale-dependent noise schedule informed by a dispersion relation, the model optimizes denoising performance and image generation in Fourier space, taking advantage of the distinct separation of macro and microscale features. Experimental validations on standard datasets demonstrate the model's capability to generate high-quality images while significantly reducing training time compared to existing image-domain diffusion models. This approach not only enhances our understanding of the generative processes in images but also opens pathways for research in generative AI, leveraging the convergence of theoretical physics, optimal transport, and machine learning principles.
- 17 January 2025
- Published by American Physical Society (APS) in Physical Review E
- Vol. 111 (1) , 015304
Renormalization group flow, optimal transport, and diffusion-based generative model
Diffusion-based generative models represent a forefront direction in generative artificial intelligence (AI) research today. Recent studies in physics have suggested that the renormalization group (RG) can be conceptualized as a diffusion process. This insight motivates us to develop a diffusion-based generative model by reversing the momentum-space RG flow. We establish a framework that interprets RG flow as optimal transport gradient flow, which minimizes a functional analogous to the Kullback-Leibler divergence, thereby bridging statistical physics and information theory. Our model applies forward and reverse diffusion processes in Fourier space, exploiting the sparse representation of natural images in this domain to efficiently separate signal from noise and manage image features across scales. By introducing a scale-dependent noise schedule informed by a dispersion relation, the model optimizes denoising performance and image generation in Fourier space, taking advantage of the distinct separation of macro and microscale features. Experimental validations on standard datasets demonstrate the model's capability to generate high-quality images while significantly reducing training time compared to existing image-domain diffusion models. This approach not only enhances our understanding of the generative processes in images but also opens pathways for research in generative AI, leveraging the convergence of theoretical physics, optimal transport, and machine learning principles.
- 26 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 5, 570-571
Erratum to “LightVeriFL: A Lightweight and Verifiable Secure Aggregation for Federated Learning”
This article addresses errors in [1] . Equation (2) contained an error wherein x was not bold. It is corrected below.
- 26 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 5, 570-571
Erratum to “LightVeriFL: A Lightweight and Verifiable Secure Aggregation for Federated Learning”
This article addresses errors in [1] . Equation (2) contained an error wherein x was not bold. It is corrected below.
- 29 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 5, 285-301
LightVeriFL: A Lightweight and Verifiable Secure Aggregation for Federated Learning
Secure aggregation protects the local models of the users in federated learning, by not allowing the server to obtain any information beyond the aggregate model at each iteration. Naively implementing secure aggregation fails to protect the integrity of the aggregate model in the possible presence of a malicious server forging the aggregation result, which motivates verifiable aggregation in federated learning. Existing verifiable aggregation schemes either have a linear complexity in model size or require time-consuming reconstruction at the server, that is quadratic in the number of users, in case of likely user dropouts. To overcome these limitations, we propose LightVeriFL , a lightweight and communication-efficient secure verifiable aggregation protocol, that provides the same guarantees for verifiability against a malicious server, data privacy, and dropout-resilience as the state-of-the-art protocols without incurring substantial communication and computation overheads. The proposed LightVeriFL protocol utilizes homomorphic hash and commitment functions of constant length, that are independent of the model size, to enable verification at the users. In case of dropouts, LightVeriFL uses a one-shot aggregate hash recovery of the dropped-out users, instead of a one-by-one recovery, making the verification process significantly faster than the existing approaches. Comprehensive experiments show the advantage of LightVeriFL in practical settings.
- 29 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 5, 285-301
LightVeriFL: A Lightweight and Verifiable Secure Aggregation for Federated Learning
Secure aggregation protects the local models of the users in federated learning, by not allowing the server to obtain any information beyond the aggregate model at each iteration. Naively implementing secure aggregation fails to protect the integrity of the aggregate model in the possible presence of a malicious server forging the aggregation result, which motivates verifiable aggregation in federated learning. Existing verifiable aggregation schemes either have a linear complexity in model size or require time-consuming reconstruction at the server, that is quadratic in the number of users, in case of likely user dropouts. To overcome these limitations, we propose LightVeriFL , a lightweight and communication-efficient secure verifiable aggregation protocol, that provides the same guarantees for verifiability against a malicious server, data privacy, and dropout-resilience as the state-of-the-art protocols without incurring substantial communication and computation overheads. The proposed LightVeriFL protocol utilizes homomorphic hash and commitment functions of constant length, that are independent of the model size, to enable verification at the users. In case of dropouts, LightVeriFL uses a one-shot aggregate hash recovery of the dropped-out users, instead of a one-by-one recovery, making the verification process significantly faster than the existing approaches. Comprehensive experiments show the advantage of LightVeriFL in practical settings.
- 12 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 71 (6) , 3317-3332
Gradient Coding With Dynamic Clustering for Straggler-Tolerant Distributed Learning
Distributed implementations are crucial in speeding up large scale machine learning applications. Distributed gradient descent (GD) is widely employed to parallelize the learning task by distributing the dataset across multiple workers. A significant performance bottleneck for the per-iteration completion time in distributed synchronous GD is straggling workers. Coded distributed computation techniques have been introduced recently to mitigate stragglers and to speed up GD iterations by assigning redundant computations to workers. In this paper, we introduce a novel paradigm of dynamic coded computation, which assigns redundant data to workers to acquire the flexibility to dynamically choose from among a set of possible codes depending on the past straggling behavior. In particular, we propose gradient coding (GC) with dynamic clustering, called GC-DC, and regulate the number of stragglers in each cluster by dynamically forming the clusters at each iteration. With time-correlated straggling behavior, GC-DC adapts to the straggling behavior over time; in particular, at each iteration, GC-DC aims at distributing the stragglers across clusters as uniformly as possible based on the past straggler behavior. For both homogeneous and heterogeneous worker models, we numerically show that GC-DC provides significant improvements in the average per-iteration completion time without an increase in the communication load compared to the original GC scheme.
- 12 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 71 (6) , 3317-3332
Gradient Coding With Dynamic Clustering for Straggler-Tolerant Distributed Learning
Distributed implementations are crucial in speeding up large scale machine learning applications. Distributed gradient descent (GD) is widely employed to parallelize the learning task by distributing the dataset across multiple workers. A significant performance bottleneck for the per-iteration completion time in distributed synchronous GD is straggling workers. Coded distributed computation techniques have been introduced recently to mitigate stragglers and to speed up GD iterations by assigning redundant computations to workers. In this paper, we introduce a novel paradigm of dynamic coded computation, which assigns redundant data to workers to acquire the flexibility to dynamically choose from among a set of possible codes depending on the past straggling behavior. In particular, we propose gradient coding (GC) with dynamic clustering, called GC-DC, and regulate the number of stragglers in each cluster by dynamically forming the clusters at each iteration. With time-correlated straggling behavior, GC-DC adapts to the straggling behavior over time; in particular, at each iteration, GC-DC aims at distributing the stragglers across clusters as uniformly as possible based on the past straggler behavior. For both homogeneous and heterogeneous worker models, we numerically show that GC-DC provides significant improvements in the average per-iteration completion time without an increase in the communication load compared to the original GC scheme.
- Top Cited Papers
- 15 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 3 (1) , 85-97
Version Age of Information in Clustered Gossip Networks
We consider a network consisting of a single source and $n$ receiver nodes that are grouped into equal-sized clusters. Each cluster corresponds to a distinct community such that nodes that belong to different communities cannot exchange information. We use dedicated cluster heads in each cluster to facilitate communication between the source and the nodes within that cluster. Inside clusters, nodes are connected to each other according to a given network topology. Based on the connectivity levels within clusters, each node relays its current stored version of the source update to its neighboring nodes by local gossiping . We consider disconnected, ring, and fully connected network topologies for each cluster. For each of these network topologies, we characterize the average version age at each node and find the average version age scaling as a function of the network size $n$ . Next, by allowing gossiping among the cluster heads, we improve the version age scaling at the receiver nodes. Then, focusing on a ring network topology in each cluster, we introduce hierarchy to the considered clustered gossip network model without using dedicated cluster heads. Finally, we find the version age-optimum cluster sizes as a function of the source, cluster head, and node update rates through numerical evaluations.
- 15 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 3 (1) , 85-97
Top Cited PapersVersion Age of Information in Clustered Gossip Networks
We consider a network consisting of a single source and $n$ receiver nodes that are grouped into equal-sized clusters. Each cluster corresponds to a distinct community such that nodes that belong to different communities cannot exchange information. We use dedicated cluster heads in each cluster to facilitate communication between the source and the nodes within that cluster. Inside clusters, nodes are connected to each other according to a given network topology. Based on the connectivity levels within clusters, each node relays its current stored version of the source update to its neighboring nodes by local gossiping . We consider disconnected, ring, and fully connected network topologies for each cluster. For each of these network topologies, we characterize the average version age at each node and find the average version age scaling as a function of the network size $n$ . Next, by allowing gossiping among the cluster heads, we improve the version age scaling at the receiver nodes. Then, focusing on a ring network topology in each cluster, we introduce hierarchy to the considered clustered gossip network model without using dedicated cluster heads. Finally, we find the version age-optimum cluster sizes as a function of the source, cluster head, and node update rates through numerical evaluations.
- Open Access
- 27 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 326-330
Age of Gossip in Networks with Community Structure
We consider a network consisting of a single source and n receiver nodes that are grouped into m equal size communities, i.e., clusters, where each cluster includes k nodes and is served by a dedicated cluster head. The source node keeps versions of an observed process and updates each cluster through the associated cluster head. Nodes within each cluster are connected to each other according to a given network topology. Based on this topology, each node relays its current update to its neighboring nodes by local gossiping. We use the version age metric to quantify information timeliness at the receiver nodes. We consider disconnected, ring, and fully connected network topologies for each cluster. For each of these network topologies, we characterize the average version age at each node and find the version age scaling as a function of the network size n. Our results indicate that per node version age scalings of $O(\sqrt n ),O\left({{n^{\frac{1}{3}}}}\right)$, and O(log n) are achievable in disconnected, ring, and fully connected cluster models, respectively. Finally, through numerical evaluations, we determine the version age-optimum (m, k) pairs as a function of the source, cluster head, and node update rates.- 27 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 326-330
Open AccessAge of Gossip in Networks with Community Structure
We consider a network consisting of a single source and n receiver nodes that are grouped into m equal size communities, i.e., clusters, where each cluster includes k nodes and is served by a dedicated cluster head. The source node keeps versions of an observed process and updates each cluster through the associated cluster head. Nodes within each cluster are connected to each other according to a given network topology. Based on this topology, each node relays its current update to its neighboring nodes by local gossiping. We use the version age metric to quantify information timeliness at the receiver nodes. We consider disconnected, ring, and fully connected network topologies for each cluster. For each of these network topologies, we characterize the average version age at each node and find the version age scaling as a function of the network size n. Our results indicate that per node version age scalings of $O(\sqrt n ),O\left({{n^{\frac{1}{3}}}}\right)$, and O(log n) are achievable in disconnected, ring, and fully connected cluster models, respectively. Finally, through numerical evaluations, we determine the version age-optimum (m, k) pairs as a function of the source, cluster head, and node update rates. - 16 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 69 (9) , 5714-5726
Selective Encoding Policies for Maximizing Information Freshness
An information source generates independent and identically distributed status update messages from an observed random phenomenon which takes n distinct values based on a given probability mass function (PMF). These update packets are encoded at the transmitter node to be sent to a receiver node which wants to track the observed random variable with as little age as possible. The transmitter node implements a selective k encoding policy such that rather than encoding all possible n realizations, the transmitter node encodes the most probable k realizations. We consider three different policies regarding the remaining n-k less probable realizations: highest k selective encoding which disregards whenever a realization from the remaining n-k values occurs; randomized selective encoding which encodes and sends the remaining n-k realizations with a certain probability to further inform the receiver node at the expense of longer codewords for the selected k realizations; and highest k selective encoding with an empty symbol which sends a designated empty symbol when one of the remaining n-k realizations occurs. For all of these three encoding schemes, we find the average age and determine the age-optimal real codeword lengths, including the codeword length for the empty symbol in the case of the latter scheme, such that the average age at the receiver node is minimized. Through numerical evaluations for arbitrary PMFs, we show that these selective encoding policies result in a lower average age than encoding every realization, and find the corresponding age-optimal k values. Since we focus on real-valued codeword lengths in this paper, the resulting age value obtained in each case studied here serves as a lower bound to what can be attained by integer-valued codeword lengths in that case.
- 16 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 69 (9) , 5714-5726
Selective Encoding Policies for Maximizing Information Freshness
An information source generates independent and identically distributed status update messages from an observed random phenomenon which takes n distinct values based on a given probability mass function (PMF). These update packets are encoded at the transmitter node to be sent to a receiver node which wants to track the observed random variable with as little age as possible. The transmitter node implements a selective k encoding policy such that rather than encoding all possible n realizations, the transmitter node encodes the most probable k realizations. We consider three different policies regarding the remaining n-k less probable realizations: highest k selective encoding which disregards whenever a realization from the remaining n-k values occurs; randomized selective encoding which encodes and sends the remaining n-k realizations with a certain probability to further inform the receiver node at the expense of longer codewords for the selected k realizations; and highest k selective encoding with an empty symbol which sends a designated empty symbol when one of the remaining n-k realizations occurs. For all of these three encoding schemes, we find the average age and determine the age-optimal real codeword lengths, including the codeword length for the empty symbol in the case of the latter scheme, such that the average age at the receiver node is minimized. Through numerical evaluations for arbitrary PMFs, we show that these selective encoding policies result in a lower average age than encoding every realization, and find the corresponding age-optimal k values. Since we focus on real-valued codeword lengths in this paper, the resulting age value obtained in each case studied here serves as a lower bound to what can be attained by integer-valued codeword lengths in that case.
- 12 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 68 (9) , 5273-5282
Timely Distributed Computation With Stragglers
We consider a status update system in which the update packets need to be processed to extract the embedded useful information. The source node sends the acquired information to a computation unit (CU) which consists of a master node and n worker nodes. The master node distributes the received computation task to the worker nodes. Upon computation, the master node aggregates the results and sends them back to the source node to keep it updated. We investigate the age performance of uncoded and coded (repetition coded, MDS coded, and multi-message MDS (MM-MDS) coded) schemes in the presence of stragglers under i.i.d. exponential transmission delays and i.i.d shifted exponential computation times. We show that asymptotically MM-MDS coded scheme outperforms the other schemes. Furthermore, we characterize the optimal codes such that the average age is minimized.
- 12 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 68 (9) , 5273-5282
Timely Distributed Computation With Stragglers
We consider a status update system in which the update packets need to be processed to extract the embedded useful information. The source node sends the acquired information to a computation unit (CU) which consists of a master node and n worker nodes. The master node distributes the received computation task to the worker nodes. Upon computation, the master node aggregates the results and sends them back to the source node to keep it updated. We investigate the age performance of uncoded and coded (repetition coded, MDS coded, and multi-message MDS (MM-MDS) coded) schemes in the presence of stragglers under i.i.d. exponential transmission delays and i.i.d shifted exponential computation times. We show that asymptotically MM-MDS coded scheme outperforms the other schemes. Furthermore, we characterize the optimal codes such that the average age is minimized.