Searcharxiv⌕ Search

arXiv subjects

Imtiaz Ahmed

Publications and source records attributed to Imtiaz Ahmed.

At least 19 recordsLinked to original sources

Sample-efficient prediction of high-entropy alloy strength through outcome-aware robust sequential learning

Accurate prediction of high-entropy alloy (HEA) strength can guide composition and processing decisions; however, obtaining tensile-test data for HEAs can be costly and experimentally demanding. This study proposes Robust Outcome-aware Sequential Experimentation for High-Entropy Alloys (ROSE-HEA), a sample-efficient framework for predicting ultimate tensile strength (UTS) from alloy composition and processing conditions. Its acquisition policy anticipates how possible UTS outcomes update predictions and the support for complementary Gaussian process (GP) descriptions. It then reassesses the worst-case expected predictive risk remaining across a reference domain to select informative candidates. A retrospective evaluation on 501 HEA records compares ROSE-HEA with expected-improvement (EI) and upper-confidence-bound (UCB) Bayesian optimization (BO), random GP sampling, and eight conventional regressors across 30 matched runs with shared initial observations and test conditions. Starting from 25 initial observations and acquiring 100 additional responses, ROSE-HEA achieves the lowest mean root-mean-square error (RMSE), at 152.84 MPa, and the highest mean R^2, at 0.7443. Mean RMSE is reduced by 6.16% and 6.37% relative to EI and UCB, respectively. The selected observations improve prediction across six regressor families and provide broader design-space coverage. ROSE-HEA also surpasses the strongest conventional regressor's mean predictive performance using 125 rather than 185 observations, corresponding to 32.4% fewer training observations. These findings demonstrate the potential of outcome-aware robust sequential learning to improve UTS prediction in HEAs under constrained training budgets.

cs.LG↗

Availability-Aware Historical Feedback Learning for Electric Arc Furnace Temperature and Chemical Composition Prediction

Electric arc furnace (EAF) steelmaking plays an increasingly important role in recycled and lower-carbon steel production. However, variability in charged materials, energy input, and operating conditions makes accurate prediction of molten steel temperature and final chemical composition challenging. Intermittent or delayed measurements limit the information available for timely prediction. This study develops an availability-aware historical-feedback learning framework for predicting EAF endpoint temperature and the final concentrations of twelve chemical elements. Eight industrial data sources are integrated into three progressively enriched predictor representations comprising 19 static, 39 temporal, and 47 history-informed features. Historical outcomes are incorporated only when eligible under an assumed 60-minute measurement-release delay. Using 19,738 temperature heats and 3,341 chemistry heats, twelve tuned regression algorithms are evaluated through chronological forward validation. The proposed historical-feedback representation reduces root mean squared error (RMSE) in 147 of 156 matched algorithm-target comparisons. For temperature prediction, ExtraTrees achieves an RMSE of 12.290 degrees C, representing a 5.54 percent reduction compared with its temporal-only counterpart. Historical-feature ablation and feedback-delay sensitivity analyses demonstrate the importance of recent outcome information and its availability. In a separate retrospective later-period evaluation, lightweight adaptive residual correction reduces temperature RMSE from 12.502 to 12.275 degrees C without retraining the underlying model. Exploratory deep learning comparisons and target-specific feature-attribution analyses provide additional insights into predictive behavior. The results establish historical outcome availability and sequential feedback as important considerations for EAF endpoint prediction.

cs.LG↗

Theory-Guided Instance-Dependent Early Stopping via Second-Order Loss Dynamics

Instance-dependent early stopping (IES) reduces training computation by skipping backpropagation for examples whose losses have stabilized, but the second-order loss-difference criterion used by IES lacks a theoretical justification. We develop Theory-Guided Instance-Dependent Early Stopping (TG-IES), which analyzes this criterion under explicit assumptions and derives a noise-calibrated mastery threshold and a conditional stability bound for instance exclusion. We show that second-order differencing has a favorable bias-variance trade-off over first- and third-order differences in a specific signal-to-noise regime, and that its signal contains both gradient-drift and curvature terms. TG-IES derives its stopping threshold and patience from training-run statistics rather than using the manually selected threshold of IES. Across CIFAR-10 and CIFAR-100, TG-IES saves 53-58% of backpropagation instances in its main convolutional settings while keeping accuracy within 0.1-0.9 percentage points of full training; in the primary ResNet-18/CIFAR-10 setting, this corresponds to 35.7% FLOP-normalized savings. The method also transfers to ViT-Tiny, where it achieves smaller savings and incurs a modest accuracy cost. These results provide a theoretical basis for second-order instance-dependent early stopping and show that theory-guided calibration can substantially reduce training computation under the assumptions and experimental settings studied.

cs.LG↗

AutoPoly-HE: Autonomous Design of Polynomial Activations for Privacy-Preserving Encrypted Inference

Privacy-preserving machine learning has become critical for deploying artificial intelligence in sensitive domains such as healthcare, finance, and infrastructure monitoring. Homomorphic encryption (HE) enables secure inference on encrypted data. Despite its advantages, HE is not compatible with nonlinear activation functions found in machine learning models. Existing methods mitigate this problem by manually designing polynomial approximations for these activation functions. However, these functions do not account for the differences in dataset characteristics or model architecture. Furthermore, these functions are also limited to the accuracies of convolutional neural network (CNN) models. In this work, we propose an autonomous framework that selects polynomial activation functions tailored to each dataset and model. Using this framework, we analyze the interdependence between polynomial activation design and model architecture by evaluating several CNN ResNet and Vision Transformer models across multiple datasets. Experimental results demonstrate that the proposed framework generalizes across multiple architectures, including ResNet-18, ResNet-34, ResNet-50, ViT-S/16, ViT-B/16, and ViT-L/16. Across all datasets, transformer-based models maintain higher accuracy under polynomial approximation, while convolutional models exhibit increased degradation as task complexity grows. In addition, latency analysis reveals that the proposed CLS token based inference pipeline significantly reduces computational overhead by eliminating depth-dependent operations, shifting the primary cost to encryption and decryption. These findings demonstrate that the proposed method not only adapts polynomial activations across architectures, but also enables efficientencrypted inference through both activation design and pipeline optimization.

cs.CR↗

DCM-SAM: Defect-Conditioned Mixture of LoRA Experts for NPU-Deployed AM Defect Segmentation

Metal additive manufacturing parts are inspected by X-ray computed tomography, where labelled data is scarce, the pores and inclusions that matter span a few pixels, and inspection must happen at the machine. We present DCM-SAM, a defect-conditioned adaptive mixture of LoRA experts: one frozen Segment Anything backbone carries a separate Conv-LoRA expert bank and mask decoder per defect class, each trained in its own pass, without prompts, on synthetic slices alone, updating only 4.4% of the parameters. On benchmarks that XCT-SAM reports, DCM-SAM improves on every baseline for both classes from a ViT-B backbone against their ViT-H, and reaches 64.2% pore IoU on real NIST scans having seen no real images during training. Deployment then exposes what adaptation work rarely measures: on a Qualcomm Hexagon NPU, ViT-H and ViT-L compile yet cannot allocate at 1024x1024 image resolution, since activations rather than weights exceed the device ceiling, and quantizing weights does not help. ViT-B alone runs, but the adapted encoder then fails to allocate where the stock one succeeds, until a numerically identical rewrite of the attention lets the complete DCM-SAM run in FP16 at 1024x1024, with no operator falling back to the CPU, masks within 0.01% of pixels of the FP32 reference. Code: https://github.com/MushfiqShovon/DCM-SAM.

cs.CV↗

Digital Twin Enhanced Channel Twin for AI-Native CSI Inference: Generalizability and Scalability

Accurate channel state information (CSI) is critical for advanced multi-antenna wireless networks. While high-fidelity and site-specific ray-tracing (RT) equipped wireless digital twins can overcome overhead for CSI acquisition. However, computing deterministic, calibrated RT based CSI from a wireless digital twin for every orthogonal frequency-division multiplexing (OFDM) symbol violates the strict microsecond latency budgets of the 5G NR numerology. To overcome this computational bottleneck, this paper investigates three approaches within a calibrated 3D digital twin framework, namely (i) the generalization of the channel twin, (ii) the performance enhancement using a neural receiver, and (iii) a data-driven interpolation framework for scalability. We compute high-precision CSI for a sparse subset of temporal anchors and employ an attention-based Transformer to predict the remaining symbols. Unlike polynomial splines or sequential long short-term memory (LSTM) networks, the Transformer exploits a global receptive field to capture the non-linear multipath dynamics while enabling parallelizable, real-time inference. To achieve spatial scalability, we introduce channel twin generalization. By fine-tuning the 3D RT models alongside the Transformer, the framework leverages the CSI dataset of one location to infer the channel behavior of an unseen environment. Transfer learning further adapts the model to a new environment using only a small fraction of locally collected data. Simulation results demonstrate that the proposed architecture substantially outperforms the baseline interpolators, achieves robust spatial transferability, and lowers the bit error rate through the unified neural receiver. These results establish a scalable, environment-agnostic foundation of distributed channel twins for high-quality, low-overhead CSI acquisition in next-generation cellular networks.

eess.SP↗

SENTINEL: A Multi-Pathway Architecture for Detecting Living-Off-the-Land APT Attacks on Windows Command Lines

Living-Off-the-Land (LOTL) is the dominant evasion technique of Advanced Persistent Threat (APT) actors, exploiting legitimate Windows utilities to conduct malicious operations without deploying custom malware and enabling state-sponsored campaigns to maintain persistent access within military and critical defense infrastructure for extended periods. Existing detection methods fail against obfuscated commands and multi-stage attack sequences, as demonstrated by the Volt Typhoon APT campaign, which maintained undetected access to U.S. critical infrastructure for over 18 months using exclusively signed Windows utilities. We present SENTINEL, a multi-pathway architecture integrating BERT-based semantic encoding, character-level CNN for obfuscation invariance, inter-command attention for multi-stage pattern recognition, and autoencoder-based anomaly scoring. Evaluated on a balanced Volt Typhoon benchmark derived from Microsoft and CISA threat intelligence advisories, SENTINEL achieves 92.0% accuracy on documented state-sponsored attack commands and 91.2% on obfuscated variants, compared to 74.0% and 72.0% for standalone BERT. Per-class analysis reveals that models achieving over 98% overall validation accuracy on imbalanced data exhibit only 44-58% malicious recall on balanced adversarial sets. Character-level processing contributes 5.6 percentage points of obfuscation invariance, and the 8.0 percentage point gap over augmentation-only baselines confirms structural architectural value beyond data-driven robustness alone.

cs.CR↗

Calibrating the Digital Twin Channel: Statistics-Consistent Sim-to-Lab Adaptation for W-Band Industrial OFDM Links

Digital twins (DTs) can reduce over-the-air validation cost in industrial wireless networks, but their utility depends on the fidelity of the underlying channel twin (CT). At W-band, site-specific ray tracing captures deterministic propagation geometry, yet its channel frequency responses (CFRs) do not reproduce the small-scale impairments and capture-to-capture variability observed in laboratory orthogonal frequency-division multiplexing (OFDM) measurements above 90 GHz. This paper proposes Statistics-Consistent Sim-to-Lab Adaptation (SC-SLA), a calibration framework that improves the fidelity of a 95 GHz Sionna ray-traced CT toward that of the testbed by aligning the mean power delay profile (PDP), the distribution of root-mean-square delay spread ($τ_{\mathrm{rms}}$), and per-subcarrier statistics at 50 MHz sampling bandwidth. SC-SLA uses a generative adversarial network (GAN)-inspired, cycle-consistent architecture with ResNet generators and batch-level channel-statistics losses on the PDP, sub-band PDP, $τ_{\mathrm{rms}}$ moments and quantiles, and normalized mean-square error (NMSE) of the mean CFR-magnitude profile. The framework is non-adversarial and requires neither paired simulated/measured samples nor discriminators. On held-out 95 GHz data, SC-SLA reduces the $τ_{\mathrm{rms}}$ Kolmogorov-Smirnov (KS) statistic from 0.86 to 0.050 relative to the impairment-augmented ray-traced input, and by 44% (from 0.089 to 0.050) relative to the strongest of four supervised baselines (FCNN, CNN1D, BiLSTM, and UNet1D). Without retraining, the same checkpoint also generalizes to 92-94 GHz carriers, where it achieves the lowest PDP and CFR-magnitude errors among all baselines while reducing the $τ_{\mathrm{rms}}$-distribution mismatch relative to the uncalibrated twin.

eess.SP↗

XCT-SAM: Sequential Parameter-Efficient Domain Adaptation of SAM for Industrial XCT Defect Segmentation

Defect segmentation in additive manufacturing (AM) X-ray computed tomography (XCT) images remains challenging due to severe class imbalance and large distribution shifts across scan conditions. Although recent foundation models such as the Segment Anything Model (SAM) provide strong general-purpose segmentation priors, their natural-image pre-training transfers poorly to the AM XCT domain, where defects appear as subtle non-semantic microstructural anomalies. Moreover, adapting SAM to the AM domain is further limited by the large domain gap and scarcity of labeled real XCT data. We present XCT-SAM, a sequential parameter-efficient adaptation framework for AM XCT defect segmentation. Instead of adapting SAM directly from natural images to XCT data, we first fine-tune Conv-LoRA adapters on an alloy-microstructure dataset and subsequently transfer the adapted model to XCT images, progressively bridging the domain gap. Using Conv-LoRA adapters with rank r=2, the framework injects convolutional spatial inductive bias into SAM's backbone while training approximately 4.15M parameters and keeping over 99% of the model frozen. We evaluate XCT-SAM on out-of-distribution CycleGAN-XCT benchmarks and real-world NIST XCT scans. Across both settings, XCT-SAM consistently outperforms zero-shot SAM and other domain-adapted SAM baselines, achieving the best overall IoU and Dice scores. These results demonstrate the effectiveness of intermediate domain adaptation with parameter-efficient adapters for industrial XCT defect segmentation. The source code is publicly available at https://github.com/Mahedi-61/XCT-SAM.git

cs.CV↗

Binary Gaussian Copula Synthesis: an LLM-powered data augmentation framework for early dialysis prediction in chronic kidney disease

Only a small fraction of patients with chronic kidney disease (CKD) progress to dialysis, creating severe class imbalance that limits the performance of machine learning models for early dialysis prediction. This challenge is compounded by the binary structure of electronic health record (EHR) data, for which most existing augmentation methods were not designed. We propose Binary Gaussian Copula Synthesis (BGCS), a two-stage data augmentation method tailored to binary clinical data. BGCS first generates synthetic minority-class samples using a Gaussian copula framework that explicitly models pairwise dependencies among binary features, then applies a fine-tuned GPT-2 classifier to filter out clinically implausible samples before training. We evaluated BGCS on a real-world EHR dataset of 15,169 patients with CKD from West Virginia collected between 2008 and 2022, benchmarking it against SMOTE, CTGAN, and standard Gaussian Copula across four machine learning classifiers over 25 independent runs. BGCS consistently outperformed all comparison methods, achieving the highest minority-class recall for 90-day dialysis prediction, with median values ranging from 0.78 to 0.87 across classifiers, and the strongest distributional fidelity to real data, with a mean p-value of 0.68 across features. The best-performing BGCS-augmented model was integrated into an interpretable decision tree-based clinical decision support system for dialysis risk stratification, with electrolyte imbalances, cardiovascular comorbidities, and renal monitoring indicators emerging as the most influential predictive features. These findings suggest that augmentation methods designed for the structural properties of binary EHR data can meaningfully improve early dialysis risk prediction and support the development of interpretable clinical decision-support tools for CKD care.

stat.AP↗

STRIDe: Cross-Coupled STT-MRAM Enabling Robust In-Memory-Computing for Deep Neural Network Accelerators

As deep neural network (DNN) models are growing exponentially in size, their deployment on resource-constrained edge platforms is becoming increasingly challenging. In-memory-computing (IMC) with non-volatile memories (NVMs) has emerged as a potential solution by virtue of its higher energy efficiency compared to standard DNN hardware platforms. Amongst various NVMs, STT-MRAM is highly promising owing to its high endurance and other benefits. However, their IMC implementation is challenging because of their inherently low distinguishability. This issue is exacerbated due to array non-idealities and process-variations, leading to poor IMC robustness and severe inference accuracy degradation. To address this problem, we propose STRIDe - STT-MRAM-based IMC leveraging cross-coupling action to boost the bitcell-level high-to-low current ratio to up to 8000. We propose two flavors of STRIDe designs, both offering robust IMC for inputs and weights in {-1, 1}(XNOR-IMC) and {0, 1}(AND-IMC) regime. Our evaluations for STRIDe arrays show up to 3.86x and 1.77x sense margin (SM) improvement for XNOR-IMC and AND-IMC, respectively, and up to 27.6% read disturb margin (RDM) improvement over standard MRAM-IMC designs. The enhanced robustness of STRIDe translates to near-software inference accuracies (considering crossbar non-idealities and process variations) for ResNet18 BNN and 4-bit DNN trained on CIFAR10 dataset. We observe accuracy improvements of up to 70% (for BNN) and up to 35%(for 4-bit DNN) over standard MRAM designs, albeit with some energy-area-latency penalty.

cs.ET↗

Digital-Twin Empowered Deep Reinforcement Learning For Site-Specific Radio Resource Management in NextG Wireless Aerial Corridor

Joint base station (BS) association and beam selection in multi-UAV aerial corridors constitutes a challenging radio resource management (RRM) problem. It is driven by high-dimensional action spaces, need for substantial overhead to acquire global channel state information (CSI), rapidly varying propagation channels, and stringent latency requirements. Conventional combinatorial optimization methods, while near-optimal, are computationally prohibitive for real-time operation in such dynamic environments. While learning-based approaches can mitigate computational complexity and CSI overhead, the need for extensive site-specific (SS) datasets for model training remains a key challenge. To address these challenges, we develop a Digital Twin (DT)-enabled two-stage optimization framework that couples physics-based beam gain modeling with DRL for scalable online decision-making. In the first stage, a channel twin (CT) is constructed using a high-fidelity ray-tracing solver with geo-spatial contexts, and network information to capture SS propagation characteristics, and dual annealing algorithm is employed to precompute optimal transmission beam directions. In the second stage, a Multi-Head Proximal Policy Optimization (MH-PPO) agent, equipped with a scalable multi-head actor-critic architecture, is trained on the DT-generated channel dataset to directly map complex channel and beam states to jointly execute UAV-BS-beam association decisions. The proposed PPO agent achieves a 44%-121% improvement over DQN and 249%-807% gain over traditional heuristic based optimization schemes in a dense UAV scenario, while reducing inference latency by several orders of magnitude. These results demonstrate that DT-driven training pipelines can deliver high-performance, low-latency RRM policies tailored to SS deployments suitable for real-time resource management in next-generation aerial corridor networks.

eess.SP↗

Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling

Motion Transfer is a technique that synthesizes videos by transferring motion dynamics from a driving video to a source image. In this work we propose a deep learning-based framework to enable real-time video motion transfer which is critical for enabling bandwidth-efficient applications such as video conferencing, remote health monitoring, virtual reality interaction, and vision-based anomaly detection. This is done using keypoints which serve as semantically meaningful, compact representations of motion across time. To enable bandwidth savings during video transmission we perform forecasting of keypoints using two generative time series models VRNN and GRU-NF. The predicted keypoints are transformed into realistic video frames using an optical flow-based module paired with a generator network, thereby enabling efficient, low-frame-rate video transmission. Based on the application this allows the framework to either generate a deterministic future sequence or sample a diverse set of plausible futures. Experimental results demonstrate that VRNN achieves the best point-forecast fidelity (lowest MAE) in applications requiring stable and accurate multi-step forecasting and is particularly competitive in higher-uncertainty, multi-modal settings. This is achieved by introducing recurrently conditioned stochastic latent variables that carry past contexts to capture uncertainty and temporal variation. On the other hand the GRU-NF model enables richer diversity of generated videos while maintaining high visual quality. This is realized by learning an invertible, exact-likelihood mapping between the keypoints and their latent representations which supports rich and controllable sampling of diverse yet coherent keypoint sequences. Our work lays the foundation for next-generation AI systems that require real-time, bandwidth-efficient, and semantically controllable video generation.

cs.CV↗

SD-CGAN: Conditional Sinkhorn Divergence GAN for DDoS Anomaly Detection in IoT Networks

The increasing complexity of IoT edge networks presents significant challenges for anomaly detection, particularly in identifying sophisticated Denial-of-Service (DoS) attacks and zero-day exploits under highly dynamic and imbalanced traffic conditions. This paper proposes SD-CGAN, a Conditional Generative Adversarial Network framework enhanced with Sinkhorn Divergence, tailored for robust anomaly detection in IoT edge environments. The framework incorporates CTGAN-based synthetic data augmentation to address class imbalance and leverages Sinkhorn Divergence as a geometry-aware loss function to improve training stability and reduce mode collapse. The model is evaluated on exploitative attack subsets from the CICDDoS2019 dataset and compared against baseline deep learning and GAN-based approaches. Results show that SD-CGAN achieves superior detection accuracy, precision, recall, and F1-score while maintaining computational efficiency suitable for deployment in edge-enabled IoT environments.

cs.LG↗

Boosting Predictive Performance on Tabular Data through Data Augmentation with Latent-Space Flow-Based Diffusion

Severe class imbalance is common in real-world tabular learning, where rare but important minority classes are essential for reliable prediction. Existing generative oversampling methods such as GANs, VAEs, and diffusion models can improve minority-class performance, but they often struggle with tabular heterogeneity, training stability, and privacy concerns. We propose a family of latent-space, tree-driven diffusion methods for minority oversampling that use conditional flow matching with gradient-boosted trees as the vector-field learner. The models operate in compact latent spaces to preserve tabular structure and reduce computation. We introduce three variants: PCAForest, which uses linear PCA embedding; EmbedForest, which uses a learned nonlinear embedding; and AttentionForest, which uses an attention-augmented embedding. Each method couples a GBT-based flow with a decoder back to the original feature space. Across 11 datasets from healthcare, finance, and manufacturing, AttentionForest achieves the best average minority recall while maintaining competitive precision, calibration, and distributional similarity. PCAForest and EmbedForest reach similar utility with much faster generation, offering favorable accuracy-efficiency trade-offs. Privacy evaluated with nearest-neighbor distance ratio and distance-to-closest-record is comparable to or better than the ForestDiffusion baseline. Ablation studies show that smaller embeddings tend to improve minority recall, while aggressive learning rates harm stability. Overall, latent-space, tree-driven diffusion provides an efficient and privacy-aware approach to high-fidelity tabular data augmentation under severe class imbalance.

cs.LG↗

KANGURA: Kolmogorov-Arnold Network-Based Geometry-Aware Learning with Unified Representation Attention for 3D Modeling of Complex Structures

Microbial Fuel Cells (MFCs) offer a promising pathway for sustainable energy generation by converting organic matter into electricity through microbial processes. A key factor influencing MFC performance is the anode structure, where design and material properties play a crucial role. Existing predictive models struggle to capture the complex geometric dependencies necessary to optimize these structures. To solve this problem, we propose KANGURA: Kolmogorov-Arnold Network-Based Geometry-Aware Learning with Unified Representation Attention. KANGURA introduces a new approach to three-dimensional (3D) machine learning modeling. It formulates prediction as a function decomposition problem, where Kolmogorov-Arnold Network (KAN)- based representation learning reconstructs geometric relationships without a conventional multi- layer perceptron (MLP). To refine spatial understanding, geometry-disentangled representation learning separates structural variations into interpretable components, while unified attention mechanisms dynamically enhance critical geometric regions. Experimental results demonstrate that KANGURA outperforms over 15 state-of-the-art (SOTA) models on the ModelNet40 benchmark dataset, achieving 92.7% accuracy, and excels in a real-world MFC anode structure problem with 97% accuracy. This establishes KANGURA as a robust framework for 3D geometric modeling, unlocking new possibilities for optimizing complex structures in advanced manufacturing and quality-driven engineering applications.

cs.AI↗

Digital-Twin Empowered Site-Specific Radio Resource Management in 5G Aerial Corridor

Base station (BS) association and beam selection in multi-cell drone corridor networks present unique challenges due to the high altitude, mobility and three-dimensional movement of drones. These factors lead to frequent handovers and complex beam alignment issues, especially in environments with dense BS deployments and varying signal conditions. To address these challenges, this paper proposes a channel-twin (CT) enabled resource-allocation framework for drone-corridor communications, where the CT constitutes the radio-channel component of a broader digital-twin (DT) environment. The CT supplies high-fidelity channel-state information (CSI), which drives a two-stage optimization procedure. In Stage 1, array-level beamforming weights at each BS are selected to maximize antenna gain. In Stage 2, the framework jointly optimizes drone-BS-beam associations at discrete corridor way-points to maximize end-to-end throughput. Simulation results confirm that the CT-driven strategy delivers significant throughput gains over baseline methods across diverse operating scenarios, validating the effectiveness of integrating precise digital-twin channel models with cross-layer resource optimization.

cs.IT↗

LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention

Existing contextual multi-armed bandit (MAB) algorithms fail to effectively capture both long-term trends and local patterns across all arms, leading to suboptimal performance in environments with rapidly changing reward structures. They also rely on static exploration rates, which do not dynamically adjust to changing conditions. To overcome these limitations, we propose LNUCB-TA, a hybrid bandit model integrating a novel nonlinear component (adaptive k-Nearest Neighbors (k-NN)) for reducing time complexity, alongside a global-and-local attention-based exploration mechanism. Our approach uniquely combines linear and nonlinear estimation techniques, with the nonlinear module dynamically adjusting k based on reward variance to enhance spatiotemporal pattern recognition. This reduces the likelihood of selecting suboptimal arms while improving reward estimation accuracy and computational efficiency. The attention-based mechanism ranks arms by past performance and selection frequency, dynamically adjusting exploration and exploitation in real time without requiring manual tuning of exploration rates. By integrating global attention (assessing all arms collectively) and local attention (focusing on individual arms), LNUCB-TA efficiently adapts to temporal and spatial complexities. Empirical results show LNUCB-TA significantly outperforms state-of-the-art linear, nonlinear, and hybrid bandits in cumulative and mean reward, convergence, and robustness across different exploration rates. Theoretical analysis further confirms its reliability with a sub-linear regret bound.

stat.ML↗