arXiv subjects

Busra Tegin

Publications and source records attributed to Busra Tegin.

10 recordsLinked to original sources

arXiv2026

Cluster-Aware Over-the-Air Federated Learning with Energy-Harvesting Devices: From Global Training to Model Personalization

Federated learning (FL) enables distributed optimization and learning across decentralized edge devices while preserving data privacy, but its performance is fundamentally constrained by heterogeneous data distributions, limited communication resources, and energy availability. In practical wireless networks, mobile devices (MDs) often exhibit diverse data and learning objectives, naturally forming clusters of users with jointly trainable models. When devices rely on energy harvesting (EH), stochastic energy arrivals further complicate participation and scheduling under communication constraints. In this work, we study over-the-air (OTA) FL with EH MDs under heterogeneous data distributions, and investigate two closely related learning objectives within a unified framework: one aiming for a more representative global model by reducing data bias, and the other learning more personalized cluster-specific models by exploiting this bias. In the global training mode, cluster information guides energy- and diversity-aware scheduling, ensuring that the scheduled active users provide a more representative aggregate update. In the personalization mode, the same cluster structure defines cluster-level learning objectives and OTA recovery targets, enabling the parameter server to train multiple cluster-specific models through simultaneous transmissions over the wireless multiple-access channel. Numerical results demonstrate that the proposed unified framework improves fairness or personalization, depending on the operating mode, while reducing communication overhead.

cs.LG↗

arXiv2026

Learning-Enhanced Composite DNA Data Storage Under Sampling Randomness and IDS Errors

DNA data storage offers a high-density, long-term alternative to conventional storage systems, addressing the exponential growth of digital data. Composite DNA extends this paradigm by leveraging mixtures of nucleotides to increase storage capacity beyond the four standard bases. In this work, composite DNA storage is modeled as a multinomial channel, and an analogy to digital modulation is established by representing composite letters on the three-dimensional probability simplex. To mitigate errors caused by sampling randomness, we derive transition probabilities for each constellation point which enables the computation of bit-wise log-likelihood ratios (LLRs) to employ practical channel codes for error correction. The framework is then extended to substitution and insertion-deletion-substitution (IDS) channels by proposing constellation update rules that account for these impairments. For the substitution channel, exact constellation updates enable exact LLR computation. In contrast, for the IDS channel, the large number of possible cases necessitates an approximate update rule, yielding approximate LLRs. To address this limitation, we further propose two learning-enhanced receiver architectures: (1) RhoNet, a learning-assisted model-based method that refines constellation points prior to analytical LLR computation, and (2) LLRNet, which directly estimates LLRs, representing a progressive transition from model-based analytical estimation to fully data-driven processing. Numerical results demonstrate reliable performance with existing low-density parity-check (LDPC) codes.

cs.IT↗

arXiv2025

On the Capacity of Insertion Channels for Small Insertion Probabilities

Channels with synchronization errors, such as deletion and insertion errors, are crucial in DNA storage, data reconstruction, and other applications. These errors introduce memory to the channel, complicating its capacity analysis. This paper analyzes binary insertion channels for small insertion probabilities, identifying dominant terms in the capacity expansion and establishing capacity in this regime. Using Bernoulli(1/2) inputs for achievability and a converse based on the use of stationary and ergodic processes, we demonstrate that capacity closely aligns with achievable rates using independent and identically distributed (i.i.d.) inputs, differing only in higher-order terms.

cs.IT↗

arXiv2025

Update Estimation and Scheduling for Over-the-Air Federated Learning with Energy Harvesting Devices

We study over-the-air (OTA) federated learning (FL) for energy harvesting devices with heterogeneous data distribution over wireless fading multiple access channel (MAC). To address the impact of low energy arrivals and data heterogeneity on global learning, we propose user scheduling strategies. Specifically, we develop two approaches: 1) entropy-based scheduling for known data distributions and 2) least-squares-based user representation estimation for scheduling with unknown data distributions at the parameter server. Both methods aim to select diverse users, mitigating bias and enhancing convergence. Numerical and analytical results demonstrate improved learning performance by reducing redundancy and conserving energy.

cs.LG↗

arXiv2025

Over-the-Air Multi-Sensor Inference with Neural Networks Using Memristor-Based Analog Computing

Deep neural networks provide reliable solutions for many classification and regression tasks; however, their application in real-time wireless systems with simple sensor networks is limited due to high energy consumption and significant bandwidth needs. This study proposes a multi-sensor wireless inference system with memristor-based analog computing. Given the sensors' limited computational capabilities, the features from the network's front end are transmitted to a central device where an $L_p$-norm inspired approximation of the maximum operation is employed to achieve transformation-invariant features, enabling efficient over-the-air transmission. We also introduce a trainable over-the-air sensor fusion method based on $L_p$-norm inspired combining function that customizes sensor fusion to match the network and sensor distribution characteristics, enhancing adaptability. To address the energy constraints of sensors, we utilize memristors, known for their energy-efficient in-memory computing, enabling analog-domain computations that reduce energy use and computational overhead in edge computing. This dual approach of memristors and $L_p$-norm inspired sensor fusion fosters energy-efficient computational and transmission paradigms and serves as a practical energy-efficient solution with minimal performance loss.

cs.LG↗

arXiv2024

Capacity Approximations for Insertion Channels with Small Insertion Probabilities

Channels with synchronization errors, exhibiting deletion and insertion errors, find practical applications in DNA storage, data reconstruction, and various other domains. Presence of insertions and deletions render the channel with memory, complicating capacity analysis. For instance, despite the formulation of an independent and identically distributed (i.i.d.) deletion channel more than fifty years ago, and proof that the channel is information stable, hence its Shannon capacity exists, calculation of the capacity remained elusive. However, a relatively recent result establishes the capacity of the deletion channel in the asymptotic regime of small deletion probabilities by computing the dominant terms of the capacity expansion. This paper extends that result to binary insertion channels, determining the dominant terms of the channel capacity for small insertion probabilities and establishing capacity in this asymptotic regime. Specifically, we consider two i.i.d. insertion channel models: insertion channel with possible random bit insertions after every transmitted bit and the Gallager insertion model, for which a bit is replaced by two random bits with a certain probability. To prove our results, we build on methods used for the deletion channel, employing Bernoulli(1/2) inputs for achievability and coupling this with a converse using stationary and ergodic processes as inputs, and show that the channel capacity differs only in the higher order terms from the achievable rates with i.i.d. inputs. The results, for instance, show that the capacity of the random insertion channel is higher than that of the Gallager insertion channel, and quantifies the difference in the asymptotic regime.

cs.IT↗

arXiv2021

Towards Goal-Oriented Semantic Signal Processing: Applications and Future Challenges

Advances in machine learning technology have enabled real-time extraction of semantic information in signals which can revolutionize signal processing techniques and improve their performance significantly for the next generation of applications. With the objective of a concrete representation and efficient processing of the semantic information, we propose and demonstrate a formal graph-based semantic language and a goal filtering method that enables goal-oriented signal processing. The proposed semantic signal processing framework can easily be tailored for specific applications and goals in a diverse range of signal processing applications. To illustrate its wide range of applicability, we investigate several use cases and provide details on how the proposed goal-oriented semantic signal processing framework can be customized. We also investigate and propose techniques for communications where sensor data is semantically processed and semantic information is exchanged across a sensor network.

eess.SP↗

arXiv2021

Straggler Mitigation through Unequal Error Protection for Distributed Approximate Matrix Multiplication

Large-scale machine learning and data mining methods routinely distribute computations across multiple agents to parallelize processing. The time required for the computations at the agents is affected by the availability of local resources and/or poor channel conditions giving rise to the "straggler problem". As a remedy to this problem, we employ Unequal Error Protection (UEP) codes to obtain an approximation of the matrix product in the distributed computation setting to provide higher protection for the blocks with higher effect on the final result. We characterize the performance of the proposed approach from a theoretical perspective by bounding the expected reconstruction error for matrices with uncorrelated entries. We also apply the proposed coding strategy to the computation of the back-propagation step in the training of a Deep Neural Network (DNN) for an image classification task in the evaluation of the gradients. Our numerical experiments show that it is indeed possible to obtain significant improvements in the overall time required to achieve the DNN training convergence by producing approximation of matrix products using UEP codes in the presence of stragglers.

cs.DC↗

arXiv2021

Blind Federated Learning at the Wireless Edge with Low-Resolution ADC and DAC

We study collaborative machine learning systems where a massive dataset is distributed across independent workers which compute their local gradient estimates based on their own datasets. Workers send their estimates through a multipath fading multiple access channel with orthogonal frequency division multiplexing to mitigate the frequency selectivity of the channel. We assume that there is no channel state information (CSI) at the workers, and the parameter server (PS) employs multiple antennas to align the received signals. To reduce the power consumption and the hardware costs, we employ complex-valued low-resolution digital-to-analog converters (DACs) and analog-to-digital converters (ADCs), at the transmitter and the receiver sides, respectively, and study the effects of practical low-cost DACs and ADCs on the learning performance. Our theoretical analysis shows that the impairments caused by low-resolution DACs and ADCs, including those of one-bit DACs and ADCs, do not prevent the convergence of the federated learning algorithm, and the multipath channel effects vanish when a sufficient number of antennas are used at the PS. We also validate our theoretical results via simulations, and demonstrate that using low-resolution, even one-bit, DACs and ADCs causes only a slight decrease in the learning accuracy.

cs.IT↗

arXiv2021

Straggler Mitigation through Unequal Error Protection for Distributed Matrix Multiplication

Large-scale machine learning and data mining methods routinely distribute computations across multiple agents to parallelize processing. The time required for computation at the agents is affected by the availability of local resources giving rise to the "straggler problem" in which the computation results are held back by unresponsive agents. For this problem, linear coding of the matrix sub-blocks can be used to introduce resilience toward straggling. The Parameter Server (PS) utilizes a channel code and distributes the matrices to the workers for multiplication. It then produces an approximation to the desired matrix multiplication using the results of the computations received at a given deadline. In this paper, we propose to employ Unequal Error Protection (UEP) codes to alleviate the straggler problem. The resiliency level of each sub-block is chosen according to its norm as blocks with larger norms have higher effects on the result of the matrix multiplication. We validate the effectiveness of our scheme both theoretically and through numerical evaluations. We derive a theoretical characterization of the performance of UEP using random linear codes, and compare it the case of equal error protection. We also apply the proposed coding strategy to the computation of the back-propagation step in the training of a Deep Neural Network (DNN), for which we investigate the fundamental trade-off between precision and the time required for the computations.

cs.IT↗