Searcharxiv⌕ Search

arXiv subjects

Jeebak Mitra

Publications and source records attributed to Jeebak Mitra.

9 recordsLinked to original sources
arXiv2026

Optimizing AI Inference Across the Deployment Stack

AI deployment performance is shaped not by model architecture alone, but by interactions among compression, compiler transformations, and serving policies. Published benchmarks often report latency and throughput under incomparable conditions, limiting their use for deployment decisions. This paper presents a unified analytical treatment of inference optimization across the deployment stack. We introduce a three-layer taxonomy covering model-level techniques such as quantization, pruning, and distillation; compiler transformations such as graph fusion, layout optimization, and kernel autotuning; and system policies such as dynamic batching, admission control, and memory tiering. We formulate deployment as a constrained multi-objective optimization problem over accuracy, latency, throughput, memory footprint, and energy, and analyze a deployment-ranking functional with Pareto monotonicity and scale invariance. Roofline models show how memory-bandwidth hierarchies bound performance across precision regimes, while queuing models explain how service-time changes amplify response time under load. To improve comparability, we propose an evidence protocol that separates measured, derived, and analytical claims; limits numerical comparison to within-paper results; and requires reporting of hardware, software versions, batch semantics, and thermal state. We synthesize evidence from edge platforms, including Jetson AGX Orin and five inference frameworks; data center GPUs, including A100 and H100 with three LLM serving engines; and quantization studies across the Llama-3.1 family. The synthesis shows that deployment outcomes are governed by cross-layer interactions that no single-layer analysis can predict. We conclude with a constraint-aware selection procedure and open problems in compiler-serving co-optimization, cross-hardware performance prediction, and standardized energy reporting.

cs.SE↗
arXiv2026

TENORAN: Automating Fine-grained Energy Efficiency Profiling in Open RAN Systems

The transition to disaggregated and interoperable Open Radio Access Network (RAN) architectures and the introduction of RAN Intelligent Controllers (RICs) in O-RAN creates new resource optimization opportunities and fine-grained tuning and configuration of network components to save energy while fulfilling service demand. However, unlocking this potential requires fine-grained and accurate energy measurements across heterogeneous deployments. Three factors make this particularly challenging [...]. To address these challenges, we design the TENORAN framework, an automated measurement scaffold for fine-grained energy efficiency profiling of O-RAN deployments, and prototype it on a heterogeneous OpenShift cluster. TENORAN instruments an end-to-end deployment based on high-level specifications (e.g., gNB software stack and split options, traffic profiles), and collects synchronized performance metrics and power measurements for individual RAN components while the network is under controlled workloads including over-the-air traffic. Our experimental results demonstrate energy profiling of end-to-end experiments with xApps in the loop, energy efficiency differences between two RAN stacks, OpenAirInterface and srsRAN, in uplink and downlink, and core network power consumption trends.

cs.NI↗
arXiv2025

Graph Attention Network for Optimal User Association in Wireless Networks

With increased 5G deployments, network densification is higher than ever to support the exponentially high throughput requirements. However, this has meant a significant increase in energy consumption, leading to higher operational expenditure (OpEx) for network operators creating an acute need for improvements in network energy savings (NES). A key determinant of operational efficacy in cellular networks is the user association (UA) policy, as it affects critical aspects like spectral efficiency, load balancing etc. and therefore impacts the overall energy consumption of the network directly. Furthermore, with cellular network topologies lending themselves well to graphical abstractions, use of graphs in network optimization has gained significant prominence. In this work, we propose and analyze a graphical abstraction based optimization for UA in cellular networks to improve NES by determining when energy saving features like cell switch off can be activated. A comparison with legacy approaches establishes the superiority of the proposed approach.

cs.IT↗
arXiv2023

Deep Learning-Aided Perturbation Model-Based Fiber Nonlinearity Compensation

Fiber nonlinearity effects cap achievable rates and ranges in long-haul optical fiber communication links. Conventional nonlinearity compensation methods, such as perturbation theory-based nonlinearity compensation (PB-NLC), attempt to compensate for the nonlinearity by approximating analytical solutions to the signal propagation over optical fibers. However, their practical usability is limited by model mismatch and the immense computational complexity associated with the analytical computation of perturbation triplets and the nonlinearity distortion field. Recently, machine learning techniques have been used to optimise parameters of PB-based approaches, which traditionally have been determined analytically from physical models. It has been claimed in the literature that the learned PB-NLC approaches have improved performance and/or reduced computational complexity over their non-learned counterparts. In this paper, we first revisit the acclaimed benefits of the learned PB-NLC approaches by carefully carrying out a comprehensive performance-complexity analysis utilizing state-of-the-art complexity reduction methods. Interestingly, our results show that least squares-based PB-NLC with clustering quantization has the best performance-complexity trade-off among the learned PB-NLC approaches. Second, we advance the state-of-the-art of learned PB-NLC by proposing and designing a fully learned structure. We apply a bi-directional recurrent neural network for learning perturbation triplets that are alike those obtained from the analytical computation and are used as input features for the neural network to estimate the nonlinearity distortion field. Finally, we demonstrate through numerical simulations that our proposed fully learned approach achieves an improved performance-complexity trade-off compared to the existing learned and non-learned PB-NLC techniques.

eess.SP↗
arXiv2023

Joint PMD Tracking and Nonlinearity Compensation with Deep Neural Networks

Overcoming fiber nonlinearity is one of the core challenges limiting the capacity of optical fiber communication systems. Machine learning based solutions such as learned digital backpropagation (LDBP) and the recently proposed deep convolutional recurrent neural network (DCRNN) have been shown to be effective for fiber nonlinearity compensation (NLC). Incorporating distributed compensation of polarization mode dispersion (PMD) within the learned models can improve their performance even further but at the same time, it also couples the compensation of nonlinearity and PMD. Consequently, it is important to consider the time variation of PMD for such a joint compensation scheme. In this paper, we investigate the impact of PMD drift on the DCRNN model with distributed compensation of PMD. We propose a transfer learning based selective training scheme to adapt the learned neural network model to changes in PMD. We demonstrate that fine-tuning only a small subset of weights as per the proposed method is sufficient for adapting the model to PMD drift. Using decision directed feedback for online learning, we track continuous PMD drift resulting from a time-varying rotation of the state of polarization (SOP). We show that transferring knowledge from a pre-trained base model using the proposed scheme significantly reduces the re-training efforts for different PMD realizations. Applying the hinge model for SOP rotation, our simulation results show that the learned models maintain their performance gains while tracking the PMD.

eess.SP↗
arXiv2023

Probabilistic Amplitude Shaping and Nonlinearity Tolerance: Analysis and Sequence Selection Method

Probabilistic amplitude shaping (PAS) is a practical means to achieve a shaping gain in optical fiber communication. However, PAS and shaping in general also affect the signal-dependent generation of nonlinear interference. This provides an opportunity for nonlinearity mitigation through PAS, which is also referred to as a nonlinear shaping gain. In this paper, we introduce a linear lowpass filter model that relates transmitted symbol-energy sequences and nonlinear distortion experienced in an optical fiber channel. Based on this model, we conduct a nonlinearity analysis of PAS with respect to shaping blocklength and mapping strategy. Our model explains results and relationships found in literature and can be used as a design tool for PAS with improved nonlinearity tolerance. We use the model to introduce a new metric for PAS with sequence selection. We perform simulations of selection-based PAS with various amplitude shapers and mapping strategies to demonstrate the effectiveness of the new metric in different optical fiber system scenarios.

cs.IT↗
arXiv2022

Learning for Perturbation-Based Fiber Nonlinearity Compensation

Several machine learning inspired methods for perturbation-based fiber nonlinearity (PBNLC) compensation have been presented in recent literature. We critically revisit acclaimed benefits of those over non-learned methods. Numerical results suggest that learned linear processing of perturbation triplets of PB-NLC is preferable over feedforward neural-network solutions.

eess.SP↗
arXiv2019

Reliable Slicing of 5G Transport Networks with Dedicated Protection

In 5G networks, slicing allows partitioning of network resources to meet stringent end-to-end service requirements across multiple network segments, from access to transport. These requirements are shaping technical evolution in each of these segments. In particular, the transport segment is currently evolving in the direction of the so-called elastic optical networks (EONs), a new generation of optical networks supporting a flexible optical-spectrum grid and novel elastic transponder capabilities. In this paper, we focus on the reliability of 5G transport-network slices in EON. Specifically, we consider the problem of slicing 5G transport networks, i.e., establishing virtual networks on 5G transport, while providing dedicated protection. As dedicated protection requires large amount of backup resources, our proposed solution incorporates two techniques to reduce backup resources: (i) bandwidth squeezing, i.e., providing a reduced protection bandwidth with respect to the original request; and (ii) survivable multi-path provisioning. We leverage the capability of EONs to fine tune spectrum allocation and adapt modulation format and Forward Error Correction (FEC) for allocating rightsize spectrum resources to network slices. Our numerical evaluation over realistic case-study network topologies quantifies the spectrum savings achieved by employing EON over traditional fixed-grid optical networks, and provides new insights on the impact of bandwidth squeezing and multi-path provisioning on spectrum utilization.

cs.NI↗