64 citations · 85 across the 22 of their papers we have counts for
24 papers
Speculation at a Distance: Where Edge-Cloud Speculative Decoding Actually Pays Off
Yuan Lyu, Bharath Irukulapati, Jaya Prakash Champati
Speculative decoding (SD) accelerates LLM inference by - times when the draft and target models are co-located. This has motivated a distributed variant (DSD) that places t…
Pay for Hints, Not Answers: LLM Shepherding for Cost-Efficient Inference
Ziming Dong, Hardik Sharma, Evan O'Toole +2
Large Language Models (LLMs) deliver state-of-the-art performance on complex reasoning tasks, but their inference costs limit deployment at scale. Small Language Models (SLMs) offe…
Inference Offloading for Cost-Sensitive Binary Classification at the Edge
Vishnu Narayanan Moothedath, Umang Agarwal, Umeshraja N +3
We focus on a binary classification problem in an edge intelligence system where false negatives are more costly than false positives. The system has a compact, locally deployed mo…
Low-Regret and Low-Complexity Learning for Hierarchical Inference
Sameep Chattopadhyay, Vinay Sutar, Jaya Prakash Champati +1
This work focuses on Hierarchical Inference (HI) in edge intelligence systems, where a compact Local-ML model on an end-device works in conjunction with a high-accuracy Remote-ML m…
Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques
Adarsh Prasad Behera, Jaya Prakash Champati, Roberto Morabito +2
Recent progress in Language Models (LMs) has dramatically advanced the field of natural language processing (NLP), excelling at tasks like text generation, summarization, and quest…
Minimizing Age of Detection for a Markov Source over a Lossy Channel
Shivang Garde, Jaya Prakash Champati, Arpan Chattopadhyay
Monitoring a process/phenomenon of specific interest is prevalent in Cyber-Physical Systems (CPS), remote healthcare, smart buildings, intelligent transport, industry 4.0, etc. A k…
Exploring the Boundaries of On-Device Inference: When Tiny Falls Short, Go Hierarchical
Adarsh Prasad Behera, Paulius Daubaris, Iñaki Bravo +4
On-device inference holds great potential for increased energy efficiency, responsiveness, and privacy in edge ML systems. However, due to less capable ML models that can be embedd…
Error Bounds for the Network Scale-Up Method
Sergio Díaz-Aranda, Juan Marcos Ramírez, Mohit Daga +4
Epidemiologists and social scientists have used the Network Scale-Up Method (NSUM) for over thirty years to estimate the size of a hidden sub-population within a social network. Th…
Improved Decision Module Selection for Hierarchical Inference in Resource-Constrained Edge Devices
Adarsh Prasad Behera, Roberto Morabito, Joerg Widmer +1
The Hierarchical Inference (HI) paradigm employs a tiered processing: the inference from simple data samples are accepted at the end device, while complex data samples are offloade…
The Case for Hierarchical Deep Learning Inference at the Network Edge
Ghina Al-Atat, Andrea Fresa, Adarsh Prasad Behera +3
Resource-constrained Edge Devices (EDs), e.g., IoT sensors and microcontroller units, are expected to make intelligent decisions using Deep Learning (DL) inference at the edge of t…
Online Algorithms for Hierarchical Inference in Deep Learning applications at the Edge
Vishnu Narayanan Moothedath, Jaya Prakash Champati, James Gross
We consider a resource-constrained Edge Device (ED), such as an IoT sensor or a microcontroller unit, embedded with a small-size ML model (S-ML) for a generic classification applic…
Statistical Age-of-Information Bounds for Parallel Systems: When Do Independent Channels Make a Difference?
Markus Fidler, Jaya Champati, Joerg Widmer +1
This paper contributes tail bounds of the age-of-information of a general class of parallel systems and explores their potential. Parallel systems arise in relevant cases, such as…
Realistic Modeling of Human Timings for Wearable Cognitive Assistance
Manuel O. J. Olguín Muñoz, Vishnu N. Moothedath, Jaya Prakash Champati +3
Wearable Cognitive Assistance (WCA) applications present a challenge to benchmark and characterize due to their human-in-the-loop nature. Employing user testing to optimize system…
Edge-MultiAI: Multi-Tenancy of Latency-Sensitive Deep Learning Applications on Edge
SM Zobaed, Ali Mokhtari, Jaya Prakash Champati +2
Smart IoT-based systems often desire continuous execution of multiple latency-sensitive Deep Learning (DL) applications. The edge servers serve as the cornerstone of such IoT-based…
Offloading Algorithms for Maximizing Inference Accuracy on Edge Device Under a Time Constraint
Andrea Fresa, Jaya Prakash Champati
With the emergence of edge computing, the problem of offloading jobs between an Edge Device (ED) and an Edge Server (ES) received significant attention in the past. Motivated by th…
Energy Efficient Sampling Policies for Edge Computing Feedback Systems
Vishnu Narayanan Moothedath, Jaya Prakash Champati, James Gross
We study the problem of finding efficient sampling policies in an edge-based feedback system, where sensor samples are offloaded to a back-end server that processes them and genera…
Estimating Active Cases of COVID-19
Javier Álvarez, Carlos Baquero, Elisa Cabana +17
Having accurate and timely data on confirmed active COVID-19 cases is challenging, since it depends on testing capacity and the availability of an appropriate infrastructure to per…
Scheduling of Wireless Edge Networks for Feedback-Based Interactive Applications
Samuele Zoppi, Jaya Prakash Champati, James Gross +1
Interactive applications with automated feedback will largely influence the design of future networked infrastructures. In such applications, status information about an environmen…
On the Minimum Achievable Age of Information for General Service-Time Distributions
Jaya Prakash Champati, Ramana R. Avula, Tobias J. Oechtering +1
There is a growing interest in analysing the freshness of data in networked systems. Age of Information (AoI) has emerged as a popular metric to quantify this freshness at a given…
Detecting State Transitions of a Markov Source: Sampling Frequency and Age Trade-off
Jaya Prakash Champati, Mikael Skoglund, James Gross
We consider a finite-state Discrete-Time Markov Chain (DTMC) source that can be sampled for detecting the events when the DTMC transits to a new state. Our goal is to study the tra…
Statistical Guarantee Optimization for AoI in Single-Hop and Two-Hop Systems with Periodic Arrivals
Jaya Prakash Champati, Hussein Al-Zubaidy, James Gross
Age of Information (AoI) has proven to be a useful metric in networked systems where timely information updates are of importance. In the literature, minimizing "average age" has r…
On the Distribution of AoI for the GI/GI/1/1 and GI/GI/1/2* Systems: Exact Expressions and Bounds
Jaya Prakash Champati, Hussein Al-Zubaidy, James Gross
Since Age of Information (AoI) has been proposed as a metric that quantifies the freshness of information updates in a communication system, there has been a constant effort in und…
Performance Characterization Using AoI in a Single-loop Networked Control System
Jaya Prakash Champati, Mohammad H. Mamduhi, Karl H. Johansson +1
The joint design of control and communication scheduling in a Networked Control System (NCS) is known to be a hard problem. Several research works have successfully designed optima…
Transient Delay Bounds for Multi-Hop Wireless Networks
Jaya Prakash Champati, Hussein Al-Zubaidy, James Gross
In this article, we investigate the transient behavior of a sequence of packets/bits traversing a multi-hop wireless network. Our work is motivated by novel applications from the d…