ASAnanthram Swami

Ananthram Swami

*This is an algorithmically generated author record based on publicly available information.

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


Ananthram Swami has a total of 127 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Out-of-Distribution Detection in Computer Vision: A Comprehensive Survey and Research Challenges

    by Aqm Sazzad Sayyed, Rifat Shahriar, Milin Zhang, Ananthram Swami, Michael De Lucia, Nathaniel Bastian, Francesco Restuccia

    Neural networks deployed in high-stakes scenarios need to provide inference that is robust to out-of-distribution (OOD) inputs. Although the resilience of neural networks to such inputs has been widely investigated in the uncertainty estimation and OOD detection communities, a unified vision of these inherently intertwined problem domains is still missing. In this work, we fill this gap by providing a survey of the state of the art that brings together research on both uncertainty estimation and OOD detection, ultimately offering a consolidated view of methods, tools, and benchmarks. We categorize existing OOD techniques by the task they address (multi-class and multi-label classification, segmentation, object detection), thus exposing progress and remaining challenges beyond the usual multi-class setting. Moreover, we highlight emerging themes such as test-time adaptation for OOD detection and new theoretical results that probe its fundamental limits, thereby outlining promising and under-explored directions for future research.


  • Open Access

    To Offload or Not To Offload: Model-driven Comparison of Edge-native and On-device Processing In the Era of Accelerators

    by Nathan Ng, David Irwin, Ananthram Swami, Don Towsley, Prashant Shenoy

    Computational offloading is a promising approach to overcome client device resource constraints by moving application computations to remote servers. With the advent of specialized hardware accelerators, client devices can now perform fast local processing of tasks such as machine learning inference, reducing the need for offloading. However, edge servers with accelerators also offer faster offloading performance than was previously possible. In this paper, we present an analytic and experimental comparison of on-device processing and edge offloading across accelerator, multi-tenant, and workload scenarios to understand when to use local processing versus offloading. We present models that leverage queuing theory to derive explainable closed-form equations for end-to-end latencies, yielding quantitative performance crossover predictions to guide adaptive offloading. We validate our models across various settings and show that they achieve a mean absolute percentage error of 2.2% compared to observed latencies. We further use these models to develop a resource manager for adaptive offloading and demonstrate its effectiveness in dynamic multi-tenant edge environments.


  • Open Access

    Poster: Sparsity-enhanced Lagrangian Relaxation (SeLR) for Computation Offloading at the Edge

    by Negar Erfaniantaghvayi, Zhongyuan Zhao, Kevin Chan, Ananthram Swami, Santiago Segarra


  • Open Access

    M2HO: Mitigating the Adverse Effects of 5G Handovers on TCP

    by Zhutian Liu, Qing Deng, Zhaowei Tan, Zhiyun Qian, Xinyu Zhang, Ananthram Swami, Srikanth V. Krishnamurthy

    The advent of 5G promises high bandwidth with the introduction of mmWave technology recently, paving the way for throughput-sensitive applications. However, our measurements in commercial 5G networks show that frequent handovers in 5G, due to physical limitations of mmWave cells, introduce significant under-utilization of the available bandwidth. By analyzing 5G link-layer and TCP traces, we uncover that improper interactions between these two layers causes multiple inefficiencies during handovers. To mitigate these, we propose M2HO, a novel device-centric solution that can predict and recognize different stages of a handover and perform state-dependent mitigation to markedly improve throughput. M2HO is transparent to the firmware, base stations, servers, and applications. We implement M2HO and our extensive evaluations validate that it yields significant improvements in TCP throughput with frequent handovers.


  • Open Access

    On the Analysis and Evaluation of Proximity-based Load-balancing Policies

    by Nitish K. Panigrahy, Thirupathaiah Vasantam, Prithwish Basu, Don Towsley, Ananthram Swami, Kin K. Leung

    Distributed load balancing is the act of allocating jobs among a set of servers as evenly as possible. The static interpretation of distributed load balancing leads to formulating the load-balancing problem as a classical balls-and-bins problem with jobs (balls) never leaving the system and accumulating at the servers (bins). While most of the previous work in the static setting focus on studying the maximum number of jobs allocated to a server or maximum load , little importance has been given to the implementation cost , or the cost of moving a job/data to/from its allocated server, for such policies. This article designs and evaluates server proximity aware static load-balancing policies with a goal to reduce the implementation cost . We consider a class of proximity aware Power of Two (POT) choice-based assignment policies for allocating jobs to servers, where both jobs and servers are located on a two-dimensional Euclidean plane. In this framework, we investigate the tradeoff between the implementation cost and load-balancing performance of different allocation policies. To this end, we first design and evaluate a Spatial Power of two (sPOT) policy in which each job is allocated to the least loaded server among its two geographically nearest servers. We provide expressions for the lower bound on the asymptotic expected maximum load on the servers and prove that sPOT does not achieve classical POT load-balancing benefits. However, experimental results suggest the efficacy of sPOT with respect to expected implementation cost. We also propose two non-uniform server sampling-based POT policies that achieve the best of both implementation cost and load-balancing performance. We then extend our analysis to the case where servers are interconnected as an n -vertex graph G(S, E) . We assume each job arrives at one of the servers, u, chosen uniformly at random from the vertex set S. We then assign each job to the server with minimum load among servers u and v where v is chosen according to one of the following two policies: (i) Unif-POT( k ): Sample a server v uniformly at random from k -hop neighborhood of u; (ii) InvSq-POT( k ): Sample a server v from k -hop neighborhood of u with probability proportional to the inverse square of the distance between u and v . An extensive simulation over a wide range of topologies validates the efficacy of both the policies. Our simulation results show that both policies consistently produce a load distribution that is much similar to that of a classical POT. Depending on topology, we observe the total variation distance to be of the order of 0.002–0.08 for both the policies while achieving a 8%–99% decrease in implementation cost as compared to the classical POT.


  • Open Access

    Delay-aware Backpressure Routing Using Graph Neural Networks

    by Zhongyuan Zhao, Bojan Radojicic, Gunjan Verma, Ananthram Swami, Santiago Segarra

    We propose a throughput-optimal biased backpressure (BP) algorithm for routing, where the bias is learned through a graph neural network that seeks to minimize end-to-end delay. Classical BP routing provides a simple yet powerful distributed solution for resource allocation in wireless multi-hop networks but has poor delay performance. A low-cost approach to improve this delay performance is to favor shorter paths by incorporating pre-defined biases in the BP computation, such as a bias based on the shortest path (hop) distance to the destination. In this work, we improve upon the widely-used metric of hop distance (and its variants) for the shortest path bias by introducing a bias based on the link duty cycle, which we predict using a graph convolutional neural network. Numerical results show that our approach can improve the delay performance compared to classical BP and existing BP alternatives based on pre-defined bias while being adaptive to interference density. In terms of complexity, our distributed implementation only introduces a one-time overhead (linear in the number of devices in the network) compared to classical BP, and a constant overhead compared to the lowest-complexity existing bias-based BP algorithms.

  • Open Access

    Distributed Link Sparsification for Scalable Scheduling Using Graph Neural Networks

    by Zhongyuan Zhao, Ananthram Swami, Santiago Segarra

    Distributed scheduling algorithms for throughput or utility maximization in dense wireless multi-hop networks can have overwhelmingly high overhead, causing increased congestion, energy consumption, radio footprint, and security vulnerability. For wireless networks with dense connectivity, we propose a distributed scheme for link sparsification with graph convolutional networks (GCNs), which can reduce the scheduling overhead while keeping most of the network capacity. In a nutshell, a trainable GCN module generates node embeddings as topology-aware and reusable parameters for a local decision mechanism, based on which a link can withdraw itself from the scheduling contention if it is not likely to win. In medium-sized wireless networks, our proposed sparse scheduler beats classical threshold-based sparsification policies by retaining almost $70\%$ of the total capacity achieved by a distributed greedy max-weight scheduler with $0.4\%$ of the point-to-point message complexity and $2.6\%$ of the average number of interfering neighbors per link.

  • Monitor Placement for Additive Network Tomography

    by Ting He, Liang Ma, Ananthram Swami, Don Towsley

  • Open Access

    Failure Localization Capability: Theorem Proof and Evaluation

    by Liang Ma, Ting He, Ananthram Swami, Don Towsley, Kin K. Leung

    This is a technical report, containing all the theorem proofs and additional evaluations in paper "Network Capability in Localizing Node Failures via End-to-end Path Measurements" by Liang Ma, Ting He, Ananthram Swami, Don Towsley, and Kin K. Leung, published in IEEE/ACM Transactions on Networking, vol. 25, no. 1, pp. 434-450, 2017.