Related papers: Online Resource Allocation for Edge Intelligence w…
Optimising deep learning inference across edge devices and optimisation targets such as inference time, memory footprint and power consumption is a key challenge due to the ubiquity of neural networks. Today, production deep learning…
Artificial Intelligence Generated Content (AIGC) services can efficiently satisfy user-specified content creation demands, but the high computational requirements pose various challenges to supporting mobile users at scale. In this paper,…
Offline reinforcement learning seeks to derive improved policies entirely from historical data but often struggles with over-optimistic value estimates for out-of-distribution (OOD) actions. This issue is typically mitigated via policy…
Edge AI, which brings artificial intelligence to the edge of the network for real-time processing and decision-making, has emerged as a transformative technology across various applications. However, the deployment of Edge AI systems faces…
A recent line of work has shown a surprising connection between multicalibration, a multi-group fairness notion, and omniprediction, a learning paradigm that provides simultaneous loss minimization guarantees for a large family of loss…
Hierarchical edge-cloud computing-aided Internet of Things (IoT) networks offer low-latency and cost-efficient services to a growing number of data-intensive IoT devices. However, optimizing service placement, which involves determining the…
Recent work on neural algorithmic reasoning has investigated the reasoning capabilities of neural networks, effectively demonstrating they can learn to execute classical algorithms on unseen data coming from the train distribution. However,…
Capacity management is critical for software organizations to allocate resources effectively and meet operational demands. An important step in capacity management is predicting future resource needs often relies on data-driven analytics…
Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions. For example, given a classifier that determines loan approval based on credit scores, applicants may open…
In this paper, we study offline-to-online Imitation Learning (IL) that pretrains an imitation policy from static demonstration data, followed by fast finetuning with minimal environmental interaction. We find the na\"ive combination of…
As mobile devices increasingly become focal points for advanced applications, edge computing presents a viable solution to their inherent computational limitations, particularly in deploying large language models (LLMs). However, despite…
The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. Removing data from the dataset alone is inadequate, as machine learning models can memorize…
This paper studies an edge intelligence-based IoT network in which a set of edge servers learn a shared model using federated learning (FL) based on the datasets uploaded from a multi-technology-supported IoT network. The data uploading…
Test-time compute scaling, the practice of spending extra computation during inference via repeated sampling, search, or extended reasoning, has become a powerful lever for improving large language model performance. Yet deploying these…
Cloud computing is a reliable solution to provide distributed computation power. However, real-time response is still challenging regarding the enormous amount of data generated by the IoT devices in 5G and 6G networks. Thus, multi-access…
By provisioning inference offloading services, edge inference drives the rapid growth of AI applications at network edge. However, how to reduce the inference latency remains a significant challenge. To address this issue, we develop a…
We revisit the problem of \textit{online linear optimization} in case the set of feasible actions is accessible through an approximated linear optimization oracle with a factor $\alpha$ multiplicative approximation guarantee. This setting…
To deploy machine learning-based algorithms for real-time applications with strict latency constraints, we consider an edge-computing setting where a subset of inputs are offloaded to the edge for processing by an accurate but…
The inference of Neural Networks is usually restricted by the resources (e.g., computing power, memory, bandwidth) on edge devices. In addition to improving the hardware design and deploying efficient models, it is possible to aggregate the…
Federated edge learning is a promising technology to deploy intelligence at the edge of wireless networks in a privacy-preserving manner. Under such a setting, multiple clients collaboratively train a global generic model under the…