Related papers: pyFAST: A Modular PyTorch Framework for Time Serie…

Despite the explosion of interest in healthcare AI research, the reproducibility and benchmarking of those research works are often limited due to the lack of standard benchmark datasets and diverse evaluation metrics. To address this…

Recent research has challenged the necessity of complex deep learning architectures for time series forecasting, demonstrating that simple linear models can often outperform sophisticated approaches. Building upon this insight, we introduce…

Neural networks are the backbone of modern artificial intelligence, but designing, evaluating, and comparing them remains labor-intensive. While numerous datasets exist for training, there are few standardized collections of the models…

Transformer-based models have shown strong performance across diverse time-series tasks, but their deployment on resource-constrained devices remains challenging due to high memory and computational demand. While prior work targeting…

"PyTorch, Explain!" is a Python module integrating a variety of state-of-the-art approaches to provide logic explanations from neural networks. This package focuses on bringing these methods to non-specialists. It has minimal dependencies…

Developments in Deep Learning have significantly improved time series forecasting by enabling more accurate modeling of complex temporal dependencies inherent in sequential data. The effectiveness of such models is often demonstrated on…

pyforce is a Python package implementing Data-Driven Reduced Order Modelling techniques for applications to multi-physics problems, mainly set in the Nuclear Engineering world. The package is part of the ROSE (Reduced Order modelling with…

Evaluating time series attribution methods is difficult because real-world datasets rarely provide ground truth for which time points drive a prediction. A common workaround is to generate synthetic data where class-discriminating features…

Correlated time series (CTS) forecasting plays an essential role in many practical applications, such as traffic management and server load control. Many deep learning models have been proposed to improve the accuracy of CTS forecasting.…

Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many contemporary…

We design and implement a ready-to-use library in PyTorch for performing micro-batch pipeline parallelism with checkpointing proposed by GPipe (Huang et al., 2019). In particular, we develop a set of design components to enable…

Scientific computing requires handling large linear models, which are often composed of structured matrices. With increasing model size, dense representations quickly become infeasible to compute or store. Matrix-free implementations are…

Attention is a fundamental building block of large language models (LLMs), so there have been many efforts to implement it efficiently. For example, FlashAttention leverages tiling and kernel fusion to optimize attention. Recently, a number…

Action diffusion excels at high-fidelity action generation but incurs heavy computational costs owing to its iterative denoising nature. Despite current technologies showing promise in accelerating diffusion transformers by reusing the…

Designing effective models for learning time series representations is foundational for time series analysis. Many previous works have explored time series representation modeling approaches and have made progress in this area. Despite…

In deterministic optimization, it is typically assumed that all problem parameters are fixed and known. In practice, however, some parameters may be a priori unknown but can be estimated from contextual information. A typical…

Motivation: Modelling methods that find structure in data are necessary with the current large volumes of genomic data, and there have been various efforts to find subsets of genes exhibiting consistent patterns over subsets of treatments.…

The advent of universal time series forecasting models has revolutionized zero-shot forecasting across diverse domains, yet the critical role of data diversity in training these models remains underexplored. Existing large-scale time series…

Multivariate time series have many applications, from healthcare and meteorology to life science. Although deep learning models have shown excellent predictive performance for time series, they have been criticised for being "black-boxes"…

Memristive devices have shown great promise to facilitate the acceleration and improve the power efficiency of Deep Learning (DL) systems. Crossbar architectures constructed using these Resistive Random-Access Memory (RRAM) devices can be…