Related papers: CloudFormer: An Attention-based Performance Predic…

Autonomous parking plays a vital role in intelligent vehicle systems, particularly in constrained urban environments where high-precision control is required. While traditional rule-based parking systems struggle with environmental…

How can applications be deployed on the cloud to achieve maximum performance? This question is challenging to address with the availability of a wide variety of cloud Virtual Machines (VMs) with different performance capabilities. The…

The design choices in Transformer feed-forward neural networks have resulted in significant computational and parameter overhead. In this work, we emphasize the importance of hidden dimensions in designing lightweight FFNs, a factor often…

Unified Virtual Memory (UVM) relieves the developers from the onus of maintaining complex data structures and explicit data migration by enabling on-demand data movement between CPU memory and GPU memory. However, on-demand paging soon…

Transformer-based models have significantly advanced time series forecasting. Recent work, like the Cross-Attention-only Time Series transformer (CATS), shows that removing self-attention can make the model more accurate and efficient.…

Hyperscalars run services across a large fleet of servers, serving billions of users worldwide. These services, however, behave differently than commonly available benchmark suites, resulting in server architectures that are not optimized…

Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the…

Efficiently exploiting servers in data centers requires performance analysis methods that account not only for the stochastic nature of demand but also for server heterogeneity. Although several recent works proved optimality results for…

Transformer has become ubiquitous due to its dominant performance in various NLP and image processing tasks. However, it lacks understanding of how to generate mathematically grounded uncertainty estimates for transformer architectures.…

When solving forecasting problems including multiple time-series features, existing approaches often fall into two extreme categories, depending on whether to utilize inter-feature information: univariate and complete-multivariate models.…

Large neural networks excel at prediction tasks, but their application to design problems, such as protein engineering or materials discovery, requires solving offline model-based optimization (MBO) problems. While predictive models may not…

The temporal complexity of electronic health record (EHR) data presents significant challenges for predicting clinical outcomes using machine learning. This paper proposes ChronoFormer, an innovative transformer based architecture…

The performance of time series forecasting has recently been greatly improved by the introduction of transformers. In this paper, we propose a general multi-scale framework that can be applied to the state-of-the-art transformer-based time…

Services hosted in multi-tenant cloud platforms often encounter performance interference due to contention for non-partitionable resources, which in turn causes unpredictable behavior and degradation in application performance. To grapple…

Time series forecasting requires architectures that simultaneously achieve three competing objectives: (1) strict temporal causality for reliable predictions, (2) sub-quadratic complexity for practical scalability, and (3) multi-scale…

Multimodal remote sensing data, including spectral and lidar or photogrammetry, is crucial for achieving satisfactory land-use / land-cover classification results in urban scenes. So far, most studies have been conducted in a 2D context.…

Cloud computing has become the backbone of the computing industry and offers subscription-based on-demand services. Through virtualization, which produces a virtual instance of a computer system running in an abstracted hardware layer, it…

Transformers have shown impressive results in tabular data generation. However, they lack domain-specific inductive biases which are critical for preserving the intrinsic characteristics of tabular data. They also suffer from poor…

Accurate traffic forecasting is essential for intelligent transportation systems, supporting a wide range of real-world applications. However, it remains challenging due to two key factors:~(1) Traffic series contain heterogeneous temporal…

Transformers have excelled in many tasks including vision. However, efficient deployment of transformer models in low-latency or high-throughput applications is hindered by the computation in the attention mechanism which involves expensive…