相关论文: OTAS: An Elastic Transformer Serving System via To…
Vision Transformers (ViTs) have emerged as a foundational model in computer vision, excelling in generalization and adaptation to downstream tasks. However, deploying ViTs to support diverse resource constraints typically requires…
Optimal transport (OT) is a widely used technique for distribution alignment, with applications throughout the machine learning, graphics, and vision communities. Without any additional structural assumptions on trans-port, however, OT can…
The statistical essence of the Transformer architecture has long remained elusive: Is it a universal approximator, or a neural network version of known computational algorithms? Through rigorous algebraic proof, we show that the latter…
Since distribution shifts are likely to occur during test-time and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model after deployment, leveraging the current test data.…
Today, modern unmanned aerial vehicles (UAVs) are equipped with increasingly advanced capabilities that can run applications enabled by machine learning techniques, which require computationally intensive operations such as matrix…
Most of current Software-as-a-Service (SaaS) applications are developed as customizable service-oriented applications that serve a large number of tenants (users) by one application instance. The current rapid evolution of SaaS applications…
Autoscaling is a critical component for efficient resource utilization with satisfactory quality of service (QoS) in cloud computing. This paper investigates proactive autoscaling for widely-used scaling-per-query applications where scaling…
This paper addresses the challenges of rapid resource variation and highly uncertain task loads in cloud computing environments. It proposes an optimization method for elastic cloud resource scaling based on a multi-agent system. The method…
The increasingly wide application of Cloud Computing enables the consolidation of tens of thousands of applications in shared infrastructures. Thus, meeting the quality of service requirements of so many diverse applications in such shared…
Many optical circuit switched data center networks (DCN) have been proposed in the past to attain higher capacity and topology reconfigurability, though commercial adoption of these architectures have been minimal. One major challenge these…
Network is a major bottleneck in modern cloud databases that adopt a storage-disaggregation architecture. Computation pushdown is a promising solution to tackle this issue, which offloads some computation tasks to the storage layer to…
Offloading resource-intensive jobs to the cloud and nearby users is a promising approach to enhance mobile devices. This paper investigates a hybrid offloading system that takes both infrastructure-based networks and Ad-hoc networks into…
Corpus Aware Training (CAT) leverages valuable corpus metadata during training by injecting corpus information into each training example, and has been found effective in the literature, commonly known as the "tagging" approach. Models…
In High Performance Computing (HPC) infrastructures, the control of resources by batch systems can lead to prolonged queue waiting times and adverse effects on the overall execution times of applications, particularly in data-intensive and…
The recent surge in 3D data acquisition has spurred the development of geometric deep learning models for point cloud processing, boosted by the remarkable success of transformers in natural language processing. While point cloud…
Continual adaptation is essential for general autonomous agents. For example, a household robot pretrained with a repertoire of skills must still adapt to unseen tasks specific to each household. Motivated by this, building upon…
Users of distributed datastores that employ quorum-based replication are burdened with the choice of a suitable client-centric consistency setting for each storage operation. The above matching choice is difficult to reason about as it…
Human Activity Recognition (HAR) models often suffer from performance degradation in real-world applications due to distribution shifts in activity patterns across individuals. Test-Time Adaptation (TTA) is an emerging learning paradigm…
Recent advancements in large language models (LLMs) based on transformer architectures have sparked significant interest in understanding their inner workings. In this paper, we introduce a novel approach to modeling transformer…
We present Amos, a stochastic gradient-based optimizer designed for training deep neural networks. It can be viewed as an Adam optimizer with theoretically supported, adaptive learning-rate decay and weight decay. A key insight behind Amos…