Related papers: Low Complexity Adaptive Machine Learning Approache…

For efficient neural network inference, it is desirable to achieve state-of-the-art accuracy with the simplest networks requiring the least computation, memory, and power. Quantizing networks to lower precision is a powerful technique for…

Deep Neural Networks (DNNs) are witnessing increased adoption in multiple domains owing to their high accuracy in solving real-world problems. However, this high accuracy has been achieved by building deeper networks, posing a fundamental…

We study optimization algorithms for the finite sum problems frequently arising in machine learning applications. First, we propose novel variants of stochastic gradient descent with a variance reduction property that enables linear…

The Real-time Transport Protocol (RTP)-based real-time communications (RTC) applications, exemplified by video conferencing, have experienced an unparalleled surge in popularity and development in recent years. In pursuit of optimizing…

We consider adaptive decision-making problems where an agent optimizes a cumulative performance objective by repeatedly choosing among a finite set of options. Compared to the classical prediction-with-expert-advice set-up, we consider…

Edge machine learning can deliver low-latency and private artificial intelligent (AI) services for mobile devices by leveraging computation and storage resources at the network edge. This paper presents an energy-efficient edge processing…

Part I of this paper considered optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspace constraints that require the objectives across the network…

Computer networks have become a critical infrastructure. In fact, networks should not only meet strict requirements in terms of correctness, availability, and performance, but they should also be very flexible and support fast updates,…

Neural networks have dramatically increased our capacity to learn from large, high-dimensional datasets across innumerable disciplines. However, their decisions are not easily interpretable, their computational costs are high, and building…

Recent advancements in learning-based query performance prediction models have demonstrated remarkable efficacy. However, these models are predominantly validated using synthetic datasets focused on cardinality or latency estimations. This…

In order to utilize network resources and provide a more reliable delivery of information, multipath routing algorithms are used with a higher priority than single path routing. But providing the quality of service (QoS) requirements while…

Distributed Opportunistic Scheduling (DOS) techniques have been recently proposed to improve the throughput performance of wireless networks. With DOS, each station contends for the channel with a certain access probability. If a contention…

Next-generation services demand stringent Quality of Service (QoS) guarantees, such as per-flow bandwidth assurance, ultra-low latency, and traffic prioritization, posing significant challenges to 5G and beyond networks. As 5G network…

A framework is introduced for solving a sequence of slowly changing optimization problems, including those arising in regression and classification applications, using optimization algorithms such as stochastic gradient descent (SGD). The…

Predictable network performance is key in many low-power wireless sensor network applications. In this paper, we use machine learning as an effective technique for real-time characterization of the communication performance as observed by…

Spatio-temporal forecasting is essential for understanding future dynamics within real-world systems by leveraging historical data from multiple locations. Existing methods often prioritize the development of intricate neural networks to…

Traditional maximum entropy and sparsity-based algorithms for analytic continuation often suffer from the ill-posed kernel matrix or demand tremendous computation time for parameter tuning. Here we propose a neural network method by convex…

It remains a challenging problem to tightly estimate the worst case response time of an application in a distributed embedded system, especially when there are dependencies between tasks. We discovered that the state-of-the art techniques…

General intelligence requires systems that acquire new skills efficiently and generalize beyond their training distributions. Although program synthesis approaches have strong generalization power, they face scaling issues due to the large…

This work considers the trade-off between accuracy and test-time computational cost of deep neural networks (DNNs) via \emph{anytime} predictions from auxiliary predictions. Specifically, we optimize auxiliary losses jointly in an…