Related papers: Dias: Dynamic Rewriting of Pandas Code
On edge devices, data scarcity occurs as a common problem where transfer learning serves as a widely-suggested remedy. Nevertheless, transfer learning imposes a heavy computation burden to resource-constrained edge devices. Existing task…
Duplication can be a powerful strategy for overcoming stragglers in cloud services, but is often used conservatively because of the risk of overloading the system. We present duplicate-aware scheduling or DAS, which makes duplication safe…
This paper presents a tool for automatically exploring the design space of deep learning accelerators (DLAs). Our main advancement is Starlight, a data-driven performance model that uses transfer learning to bridge the gap between fast,…
It is becoming increasingly difficult to improve the performance of a a single process (thread) on a computer due to physical limitations. Modern systems use multi-core processors in which multiple processes (threads) may run concurrently.…
Literature reviews are essential for any researcher trying to keep up to date with the burgeoning software engineering literature. FAST$^2$ is a novel tool for reducing the effort required for conducting literature reviews by assisting the…
Genome analysis has revolutionized fields such as personalized medicine and forensics. Modern sequencing machines generate vast amounts of fragmented strings of genome data called reads. The alignment of these reads into a complete DNA…
We follow up on the idea of Lars Arge to rephrase the Reduce and Apply procedures of Binary Decision Diagrams (BDDs) as iterative I/O-efficient algorithms. We identify multiple avenues to simplify and improve the performance of his proposed…
Time series augmentation is critical for training robust deep learning models, particularly in domains where labelled data is scarce and expensive to obtain. However, existing augmentation libraries for time series, mainly written in…
Attention mechanisms, primarily designed to capture pairwise correlations between words, have become the backbone of machine learning, expanding beyond natural language processing into other domains. This growth in adaptation comes at the…
Designing a generalist scientific agent capable of performing tasks in laboratory settings to assist researchers has become a key goal in recent Artificial Intelligence (AI) research. Unlike everyday tasks, scientific tasks are inherently…
Compared with the fixed-run designs, the sequential adaptive designs (SAD) are thought to be more efficient and effective. Efficient global optimization (EGO) is one of the most popular SAD methods for expensive black-box optimization…
Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing…
Attention-based models demand flexible hardware to manage diverse kernels with varying arithmetic intensities and memory access patterns. Large clusters with shared L1 memory, a common architectural pattern, struggle to fully utilize their…
Interactive computing notebooks, such as Jupyter notebooks, have become a popular tool for developing and improving data-driven models. Such notebooks tend to be executed either in the user's own machine or in a cloud environment, having…
The study of molecular dynamics simulations is largely facilitated by analysis and visualization toolsets. However, these toolsets are often designed for specific use cases and those only, while scripting extensions to such toolsets is…
The widespread use of Deep Neural Networks (DNNs) is limited by high computational demands, especially in constrained environments. GPUs, though effective accelerators, often face underutilization and rely on coarse-grained scheduling. This…
Dynamic evaluation of language models (LMs) adapts model parameters at test time using gradient information from previous tokens and substantially improves LM performance. However, it requires over 3x more compute than standard inference.…
In the hardware design space exploration process, it is critical to optimize both hardware parameters and algorithm-to-hardware mappings. Previous work has largely approached this simultaneous optimization problem by separately exploring…
In this paper, we introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch to speed up the training of large-scale deep learning models without sacrificing model performance.…
Software libraries are the elementary building blocks of open source software ecosystems, extending the capabilities of programming languages beyond their standard libraries. Although ecosystem health is often quantified using data on…