Related papers: Rateless Codes for Low-Latency Distributed Inferen…
We consider a mobile edge computing scenario where a number of devices want to perform a linear inference $\boldsymbol{W}\boldsymbol{x}$ on some local data $\boldsymbol{x}$ given a network-side matrix $\boldsymbol{W}$. The computation is…
We propose a unified coded framework for distributed computing with straggling servers, by introducing a tradeoff between "latency of computation" and "load of communication" for some linear computation tasks. We show that the coded scheme…
Consider a mobile edge computing system in which users wish to obtain the result of a linear inference operation on locally measured input data. Unlike the offloaded input data, the model weight matrix is distributed across wireless Edge…
Large-scale distributed computing systems face two major bottlenecks that limit their scalability: straggler delay caused by the variability of computation times at different worker nodes and communication bottlenecks caused by shuffling…
Large-scale machine learning and data mining applications require computer systems to perform massive matrix-vector and matrix-matrix multiplication operations that need to be parallelized across multiple nodes. The presence of straggling…
This paper introduces REDC, a comprehensive strategy for offloading computational tasks within mobile Edge Networks (EN) to Distributed Computing (DC) after Rateless Encoding (RE). Despite the efficiency, reliability, and scalability…
Inexpensive cloud services, such as serverless computing, are often vulnerable to straggling nodes that increase end-to-end latency for distributed computation. We propose and implement simple yet principled approaches for straggler…
Large language model (LLM) inference at the network edge is a promising serving paradigm that leverages distributed edge resources to run inference near users and enhance privacy. Existing edge-based LLM inference systems typically adopt…
Matrix computations are a fundamental building-block of edge computing systems, with a major recent uptick in demand due to their use in AI/ML training and inference procedures. Existing approaches for distributing matrix computations…
In this work, a heterogeneous set of wireless devices sharing a common access point collaborates to perform a set of tasks. Using the Map-Reduce distributed computing framework, the tasks are optimally distributed amongst the nodes with the…
Next-generation wireless networks will provide users ubiquitous low-latency computing services using devices at the network edge, called mobile edge computing (MEC). The key operation of MEC, mobile computation offloading (MCO), is to…
Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching to enhance inference performance by cooperatively sharing intermediate processing states…
Edge computing is an emerging paradigm to enable low-latency applications, like mobile augmented reality, because it takes the computation on processing devices that are closer to the users. On the other hand, the need for highly scalable…
Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…
In this paper, we propose a physical-layer rateless code for wireless channels. A novel rateless encoding scheme is developed to overcome the high error floor problem caused by the low-density generator matrix (LDGM)-like encoding scheme in…
A novel Rateless-coding-assisted Multi-Packet Relaying (RMPR) protocol is proposed for large-size data spreading in mobile wireless networks. With this lightweight and robust protocol, the packet redundancy is reduced by a factor of $\sqrt…
The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…
Federated learning enables training a global model from data located at the client nodes, without data sharing and moving client data to a centralized server. Performance of federated learning in a multi-access edge computing (MEC) network…
Driven by great demands on low-latency services of the edge devices (EDs), mobile edge computing (MEC) has been proposed to enable the computing capacities at the edge of the radio access network. However, conventional MEC servers suffer…
We propose a serverless computing mechanism for distributed computation based on polar codes. Serverless computing is an emerging cloud based computation model that lets users run their functions on the cloud without provisioning or…