arXiv subjects

Sheetal Kalyani

Publications and source records attributed to Sheetal Kalyani.

At least 19 recordsLinked to original sources

arXiv2026

DRL-AdaPart: DRL-Driven Adaptive STAR-RIS Partitioning for Fair and Efficient Resource Utilization

Efficient resource utilization is proposed for simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) to ensure fair and high data rates. We optimize the number of STAR-RIS elements to be allocated to each user and maximize the sum of the user rates. To promote fairness, we introduce a soft fairness mechanism that guarantees a minimum STAR-RIS element allocation to every user. Subject to this requirement, the phase shifts of the STAR-RIS elements and the remaining element assignments are jointly optimized by harnessing an appropriately tailored deep reinforcement learning (DRL) algorithm. The proposed DRL method is also compared to Dinkelbach's algorithm and to a bespoke hybrid DRL approach. A deactivation incentive is incorporated into the DRL model for enhancing resource utilization by intelligently deactivating some of the STAR-RIS elements when not required. The proposed DRL method achieves fair and high data rates for both stationary and mobile users, while ensuring efficient resource utilization. Using the proposed DRL method, up to 34% and 23% of STAR-RIS elements can be deactivated in static and mobile scenarios, respectively, with negligible degradation in the average DL data rate.

cs.IT↗

arXiv2026

Distribution of $k$-th Maximum Order Statistics of Independent, & Non-Identical SNR random variables in $κ-μ$ fading and its applications in $6G$

This paper employs extreme value theory to establish the asymptotic distribution of the $k$-th maximum order statistics of signal to noise ratio (SNR) for a $κ-μ$ fading channel with independent and non-identically distributed (i.n.i.d.) parameters. Since $κ-μ$ encompasses well-known distributions such as Rice, Rayleigh, and Nakagami-m, the order statistics for these are also derived as special cases. We demonstrate the practical significance of our results by showcasing their applicability in several applications, including antenna selection in MIMO systems, backscatter systems, reconfigurable intelligent surfaces, and UAV-assisted relay selection systems. Furthermore, by utilizing the $k$-th maximum order statistics, we derive expressions for outage probability and average throughput of $k$-th maximum order statistics. Comprehensive Monte Carlo simulations are carried out to verify the accuracy of the proposed results.

cs.IT↗

arXiv2026

Breaking the Script Barrier: Enabling Automatic Alignment for PoS-based ASR Error Analysis in Non-Latin Scripts

Automatic Speech Recognition (ASR) systems are commonly evaluated using aggregate metrics such as Word Error Rate (WER), which do not capture the linguistic structure of errors. Fine-grained analysis, such as Part-of-Speech (PoS)-wise error characterization, requires accurate alignment between ASR hypotheses and reference transcriptions. However, existing alignment tools are often unreliable for languages written in non-Latin scripts. In this work, we address this gap by proposing a robust, automated, language-agnostic alignment mechanism applicable across ASR architectures and across languages written in both Latin and non-Latin scripts. This enables consistent alignment of hypotheses, references, and evaluation sequences, forming the basis for downstream linguistic analysis. Building on this, we employ standard PoS taggers to perform scalable and reproducible PoS-wise error analysis. Notably, we perform alignment and downstream ASR error analysis across three major segmented writing systems, namely, Abugida (Tamil, Hindi, Kannada), Alphabetic (English, Russian, Greek), and Abjad (Arabic). We further demonstrate how such error information can be leveraged during ASR training to improve metrics such as WER.

cs.CL↗

arXiv2026

BERTO: Intent-Driven Network Time Series Forecasting via Natural Language Operator Preferences

Traditional cellular traffic forecasting models are optimized for minimizing symmetric errors, leaving them indifferent to shifting operational priorities. To bridge this gap, we introduce BERTO, a BERT-based framework for traffic prediction and energy optimization in cellular networks. Built on transformer architectures, BERTO achieves high prediction accuracy while enabling a single fine-tuned model to operate across multiple forecasting regimes via natural-language operator prompts. By combining a Balancing Loss Function (BLF) with prompt-based conditioning, BERTO adaptively shifts its forecasting bias toward underprediction or overprediction depending on the operator's desired trade-off between power savings and service quality. This allows the same model to dynamically generate different decision-aware forecasts without retraining or modifying model parameters. Experiments on real-world datasets demonstrate that BERTO can operate across a flexible range of approximately 1.4 kW in power consumption while balancing 9x variation in service level agreement (SLA) violations, making it well suited for intelligent RAN deployments.

cs.LG↗

arXiv2026

Neural Equalisers for Highly Compressed Faster-than-Nyquist Signalling: Design, Performance, Complexity and Robustness

Faster-than-Nyquist (FTN) signalling has emerged as a compelling technique for enhancing spectral efficiency in bandwidth-constrained communication systems. By intentionally introducing controlled intersymbol interference (ISI), FTN allows transmission at rates exceeding the traditional Nyquist limit, unlocking new potential in high-speed data communication. However, its practical deployment remains challenged by the need for low-complexity detection strategies that can cope with the induced ISI while maintaining low latency and robust performance. We propose deep learning receivers that are resilient to non-idealities. In this paper, we present a deep learning-based framework for FTN signalling that addresses these challenges through several novel contributions. First, we propose a sliding window detection method that leverages temporal context while preserving computational efficiency. Second, we demonstrate the viability of FTN systems with very low packing factors, showing that reliable performance can be achieved even under aggressive spectral compression (up to 75\%). Our architecture is optimised for low latency and low complexity, making it suitable for real-time applications and scalable deployment. In addition, we assess the robustness of our models across varying channel conditions and noise profiles, providing insights into their generalisability and resilience.

cs.IT↗

arXiv2026

Maximizing Qubit Throughput under Buffer Decoherence and Variability in Generation

Quantum communication networks require transmission of high-fidelity, uncoded qubits for applications such as entanglement distribution and quantum key distribution. However, current implementations are constrained by limited buffer capacity and qubit decoherence, which degrades qubit quality while waiting in the buffer. A key challenge arises from the stochastic nature of qubit generation, there exists a random delay (D) between the initiation of a generation request and the availability of the qubit. This induces a fundamental trade off early initiation increases buffer waiting time and hence decoherence, whereas delayed initiation leads to server idling and reduced throughput. We model this system as an admission control problem in a finite buffer queue, where the reward associated with each job is a decreasing function of its sojourn time. We derive analytical conditions under which a simple "no lag" policy where a new qubit is generated immediately upon the availability of buffer space is optimal. To address scenarios with unknown system parameters, we further develop a Bayesian learning framework that adaptively optimizes the admission policy. In addition to quantum communication systems, the proposed model is applicable to delay sensitive IoT sensing and service systems.

quant-ph↗

arXiv2026

Federated Learning of Binary Neural Networks: Enabling Low-Cost Inference

Federated Learning (FL) preserves privacy by distributing training across devices. However, using DNNs is computationally intensive at the low-powered edge during inference. Edge deployment demands models that simultaneously optimize memory footprint and computational efficiency, a dilemma where conventional DNNs fail by exceeding resource limits. Traditional post-training binarization reduces model size but suffers from severe accuracy loss due to quantization errors. To address these challenges, we propose FedBNN, a rotation-aware binary neural network framework that learns binary representations directly during local training. By encoding each weight as a single bit $\{+1, -1\}$ instead of a $32$-bit float, FedBNN shrinks the model footprint, significantly reducing runtime (during inference) FLOPs and memory requirements in comparison to federated methods using real models. Evaluations across multiple benchmark datasets demonstrate that FedBNN significantly reduces resource consumption while performing similarly to existing federated methods using real-valued models.

cs.LG↗

arXiv2026

Tuning-Free Structured Sparse Recovery of Multiple Measurement Vectors using Implicit Regularization

Recovering jointly sparse signals in the multiple measurement vectors (MMV) setting is a fundamental problem in machine learning, but traditional methods often require careful parameter tuning or prior knowledge of the sparsity of the signal and/or noise variance. We propose a tuning-free framework that leverages implicit regularization (IR) from overparameterization to overcome this limitation. Our approach reparameterizes the estimation matrix into factors that decouple the shared row-support from individual vector entries and applies gradient descent to a standard least-squares objective. We prove that with a sufficiently small and balanced initialization, the optimization dynamics exhibit a "momentum-like" effect where the true support grows significantly faster. Leveraging a Lyapunov-based analysis of the gradient flow, we further establish formal guarantees that the solution trajectory converges towards an idealized row-sparse solution. Empirical results demonstrate that our tuning-free approach achieves performance comparable to optimally tuned established methods. Furthermore, our framework significantly outperforms these baselines in scenarios where accurate priors are unavailable to the baselines.

cs.LG↗

arXiv2026

Integrating OTFS in Airplane-Aided Next-Generation Networking

Next-generation networks explore the opportunistic assistance of airliner/high-altitude platforms (HAPs) in delivering high data rates for terrestrial networks to ensure consistent and reliable communication. When an airliner/HAP moves at very high speeds, its mobility has a substantial impact on ensuring seamless connectivity, stable signal strength, and reliable data transmission. Orthogonal time frequency space (OTFS) modulation has been shown to provide notable improvement in performance when handling Doppler effects during high-mobility situations. This paper presents an OTFS-based airplane-aided next-generation networking system. In the proposed system, the airliner/HAPs are equipped with a planar antenna array that applies null steering beamforming (NSB) at the transmitter for communication with terrestrial users. A comprehensive performance comparison between OTFS and orthogonal frequency division multiplexing (OFDM) is performed under varying airliner altitude, velocity, array dimension, and Rician factor conditions. The simulation results show that OTFS consistently outperforms OFDM, achieving a lower bit error rate (BER) and more stable performance across different airliner altitudes, velocities, array dimensions, and propagation environments.

cs.IT↗

arXiv2025

RIS, Active RIS or RDARS: A Comparative Insight Through the Lens of Energy Efficiency

Multiplicative fading is a major limitation of reconfigurable intelligent surfaces (RIS), restricting their effective coverage in both existing sub-6GHz systems and future mmWave networks. Although active RIS architectures mitigate this issue, they require high power consumption and introduce practical challenges due to the need for integrated amplifiers. Recently, reconfigurable distributed antenna and reflecting surfaces (RDARS) have been proposed to alleviate multiplicative fading through connected modes. In this work, we compare RIS, active RIS, and RDARS in terms of coverage and energy efficiency (EE) in both sub-6GHz and mmWave bands, and we investigate the impact of placement and the number of elements of reconfigurable surface (RS) on EE and coverage. The simulation results show that RDARS offers a highly energy-efficient alternative of enhancing coverage in sub-6GHz systems, while active RIS is significantly more energy-efficient in mmWave systems. Additionally, for a lower number of RS elements and for near UEs, RIS remains considerably more energy-efficient than both active RIS and RDARS.

cs.IT↗

arXiv2025

Geometry Aware Meta-Learning Neural Network for Joint Phase and Precoder Optimization in RIS

In reconfigurable intelligent surface (RIS) aided systems, the joint optimization of the precoder matrix at the base station and the phase shifts of the RIS elements involves significant complexity. In this paper, we propose a complex-valued, geometry aware meta-learning neural network that maximizes the weighted sum rate in a multi-user multiple input single output system. By leveraging the complex circle geometry for phase shifts and spherical geometry for the precoder, the optimization occurs on Riemannian manifolds, leading to faster convergence. We use a complex-valued neural network for phase shifts and an Euler inspired update for the precoder network. Our approach outperforms existing neural network-based algorithms, offering higher weighted sum rates, lower power consumption, and significantly faster convergence. Specifically, it converges faster by nearly 100 epochs, with a 0.7 bps improvement in weighted sum rate and a 1.8 dB power gain when compared with existing work. Further it outperforms the state-of-the-art alternating optimization algorithm by 0.86 bps with a 2.6 dB power gain.

cs.LG↗

arXiv2025

Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models

Whisper models have achieved remarkable progress in speech recognition; yet their large size remains a bottleneck for deployment on resource-constrained edge devices. This paper proposes a framework to design fine-tuned variants of Whisper which address the above problem. Structured sparsity is enforced via the Sparse Group LASSO penalty as a loss regularizer, to reduce the number of FLOating Point operations (FLOPs). Further, a weight statistics aware pruning algorithm is proposed. We also design our custom text normalizer for WER evaluation. On Common Voice 11.0 Hindi dataset, we obtain, without degrading WER, (a) 35.4% reduction in model parameters, 14.25% lower memory consumption and 18.5% fewer FLOPs on Whisper-small, and (b) 31% reduction in model parameters, 15.29% lower memory consumption and 16.95% fewer FLOPs on Whisper-medium; and, (c) substantially outperform the state-of-the-art Iterative Magnitude Pruning based method by pruning 18.7% more parameters along with a 12.31 reduction in WER.

cs.LG↗

arXiv2025

Tuning-Free Online Robust Principal Component Analysis through Implicit Regularization

The performance of the standard Online Robust Principal Component Analysis (OR-PCA) technique depends on the optimum tuning of the explicit regularizers and this tuning is dataset sensitive. We aim to remove the dependency on these tuning parameters by using implicit regularization. We propose to use the implicit regularization effect of various modified gradient descents to make OR-PCA tuning free. Our method incorporates three different versions of modified gradient descent that separately but naturally encourage sparsity and low-rank structures in the data. The proposed method performs comparable or better than the tuned OR-PCA for both simulated and real-world datasets. Tuning-free ORPCA makes it more scalable for large datasets since we do not require dataset-dependent parameter tuning.

cs.LG↗

arXiv2025

Source Enumeration using the Distribution of Angles: A Robust and Parameter-Free Approach

Source enumeration, the task of estimating the number of sources from the signal received by the array of antennas, is a critical problem in array signal processing. Numerous methods have been proposed to estimate the number of sources under white or colored Gaussian noise. However, their performance degrades significantly in the presence of a limited number of observations and/or a large number of sources. In this work, we propose a method leveraging the distribution of angles that performs well in (a) independent Gaussian, (b) spatially colored Gaussian, and (c) heavy-tailed noise, even when the number of sources is large. We support the supremacy of our algorithm over state-of-the-art methods with extensive simulation results.

eess.SP↗

arXiv2025

Randomness Helps Rigor: A Probabilistic Learning Rate Scheduler Bridging Theory and Deep Learning Practice

Learning rate schedulers have shown great success in speeding up the convergence of learning algorithms in practice. However, their convergence to a minimum has not been proven theoretically. This difficulty mainly arises from the fact that, while traditional convergence analysis prescribes to monotonically decreasing (or constant) learning rates, schedulers opt for rates that often increase and decrease through the training epochs. In this work, we aim to bridge the gap by proposing a probabilistic learning rate scheduler (PLRS) that does not conform to the monotonically decreasing condition, with provable convergence guarantees. To cement the relevance and utility of our work in modern day applications, we show experimental results on deep neural network architectures such as ResNet, WRN, VGG, and DenseNet on CIFAR-10, CIFAR-100, and Tiny ImageNet datasets. We show that PLRS performs as well as or better than existing state-of-the-art learning rate schedulers in terms of convergence as well as accuracy. For example, while training ResNet-110 on the CIFAR-100 dataset, we outperform the state-of-the-art knee scheduler by $1.56\%$ in terms of classification accuracy. Furthermore, on the Tiny ImageNet dataset using ResNet-50 architecture, we show a significantly more stable convergence than the cosine scheduler and a better classification accuracy than the existing schedulers.

cs.LG↗

arXiv2025

Differential Privacy with Higher Utility by Exploiting Coordinate-wise Disparity: Laplace Mechanism Can Beat Gaussian in High Dimensions

Conventionally, in a differentially private additive noise mechanism, independent and identically distributed (i.i.d.) noise samples are added to each coordinate of the response. In this work, we formally present the addition of noise that is independent but not identically distributed (i.n.i.d.) across the coordinates to achieve tighter privacy-accuracy trade-off by exploiting coordinate-wise disparity in privacy leakage. In particular, we study the i.n.i.d. Gaussian and Laplace mechanisms and obtain the conditions under which these mechanisms guarantee privacy. The optimal choice of parameters that ensure these conditions are derived considering (weighted) mean squared and $\ell_{p}^{p}$-errors as measures of accuracy. Theoretical analyses and numerical simulations demonstrate that the i.n.i.d. mechanisms achieve higher utility for the given privacy requirements compared to their i.i.d. counterparts. One of the interesting observations is that the Laplace mechanism outperforms Gaussian even in high dimensions, as opposed to the popular belief, if the irregularity in coordinate-wise sensitivities is exploited. We also demonstrate how the i.n.i.d. noise can improve the performance in private (a) coordinate descent, (b) principal component analysis, and (c) deep learning with group clipping.

cs.CR↗

arXiv2024

The Rendezvous Between Extreme Value Theory and Next-generation Networks

Promising technologies such as massive multiple-input and multiple-output, reconfigurable intelligent reflecting surfaces, non-terrestrial networks, millimetre wave communication, ultra-reliable lowlatency communication are envisioned as the enablers for next-generation (NG) networks. In contrast to conventional communication systems meeting specific average performance requirements, NG systems are expected to meet quality-of-service requirements in extreme scenarios as well. In this regard, extreme value theory (EVT) provides a powerful framework for the design of communication systems. In this paper, we provide a comprehensive survey of advances in communication that utilize EVT to characterize the extreme order statistics of interest. We first give an overview of the history of EVT and then elaborate on the fundamental theorems. Subsequently, we discuss different problems of interest in NG communication systems and how EVT can be utilized for their analysis. We finally point out the open challenges and future directions of EVT in NG communication systems.

cs.IT↗

arXiv2024

Online waveform selection for cognitive radar

Designing a cognitive radar system capable of adapting its parameters is challenging, particularly when tasked with tracking a ballistic missile throughout its entire flight. In this work, we focus on proposing adaptive algorithms that select waveform parameters in an online fashion. Our novelty lies in formulating the learning problem using domain knowledge derived from the characteristics of ballistic trajectories. We propose three reinforcement learning algorithms: bandwidth scaling, Q-learning, and Q-learning lookahead. These algorithms dynamically choose the bandwidth for each transmission based on received feedback. Through experiments on synthetically generated ballistic trajectories, we demonstrate that our proposed algorithms achieve the dual objectives of minimizing range error and maintaining continuous tracking without losing the target.

eess.SP↗