Related papers: ML-MaxProp: Bridging Machine Learning and Delay-To…

In this paper we consider the machine learning (ML) task of predicting tipping point transitions and long-term post-tipping-point behavior associated with the time evolution of an unknown (or partially unknown), non-stationary, potentially…

This research paper investigates how machine learning-driven data replication strategies can enhance fault tolerance in large-scale distributed systems. Traditional replication methods, which rely on static configurations, often struggle to…

The optimal solution to an optimization problem depends on the problem's objective function, constraints, and size. While deep neural networks (DNNs) have proven effective in solving optimization problems, changes in the problem's size,…

This paper considers a novel travel-delay-based Max Pressure algorithm for control of arbitrary transportation networks with signalized intersections. The traditional number-of-vehicle-based Max Pressure (Original-MP) algorithm has received…

Traffic optimization challenges, such as load balancing, flow scheduling, and improving packet delivery time, are difficult online decision-making problems in wide area networks (WAN). Complex heuristics are needed for instance to find…

Mixture-of-Experts (MoE) architectures have emerged as a key strategy for scaling large language models (LLMs) efficiently. However, current MoE systems suffer from severe load imbalance, where only a small subset of experts is consistently…

Distributed multi-task learning (DMTL) effectively improves model generalization performance through the collaborative training of multiple related models. However, in large-scale learning scenarios, communication bottlenecks severely limit…

Wireless sensor networks have been increasingly used for real-time surveillance over large areas. In such applications, it is important to support end-to-end delay constraints for packet deliveries even when the corresponding flows require…

Robustly compensating network constraints such as delays and packet dropouts in networked control systems is crucial for remotely controlling dynamical systems. This work proposes a novel prediction consistent method to cope with delays and…

Delay/Disruption-Tolerant Networks (DTNs) have been around for more than a decade and have especially been proposed to be used in scenarios where communication infrastructure is unavailable. In such scenarios, DTNs can offer a best-effort…

Existing automated urban traffic management systems, designed to mitigate traffic congestion and reduce emissions in real time, face significant challenges in effectively adapting to rapidly evolving conditions. Predominantly reactive,…

Supporting ultra-reliable low-latency communications (URLLC) is a major challenge of 5G wireless networks. Stringent delay and reliability requirements need to be satisfied for both scheduled and non-scheduled URLLC traffic to enable a…

Deep Metric Learning (DML) is a prominent field in machine learning with extensive practical applications that concentrate on learning visual similarities. It is known that inputs such as Adversarial Examples (AXs), which follow a…

Delay-tolerant networking (DTN) is a term invented to describe and encompass all types of long-delay, disconnected, disrupted or intermittently-connected networks, where mobility and outages or scheduled contacts may be experienced. 'DTN'…

This paper addresses the challenge of coordinating multi-robot systems under realistic communication delays using distributed optimization. We focus on consensus ADMM as a scalable framework for generating collision-free, dynamically…

Inland waterway transportation network significantly supports the overall freight transportation of the nation. In order to ensure efficient and timely commodity transportation through this network, this study aims at developing a reliable…

Pretraining on a large-scale corpus has become a standard method to build general language models (LMs). Adapting a model to new data distributions targeting different downstream tasks poses significant challenges. Naive fine-tuning may…

Balancing the trade-off between accuracy and robustness is a long-standing challenge in time series forecasting. While most of existing robust algorithms have achieved certain suboptimal performance on clean data, sustaining the same…

Max-Plus Linear (MPL) systems are an algebraic formalism with practical applications in transportation networks, manufacturing and biological systems. In this paper, we investigate the problem of automatically analyzing the properties of…

Distributed optimization finds applications in large-scale machine learning, data processing and classification over multi-agent networks. In real-world scenarios, the communication network of agents may encounter latency that may affect…