no code implementations • 8 Mar 2023 • Victor Ferrari, Rafael Sousa, Marcio Pereira, João P. L. de Carvalho, José Nelson Amaral, José Moreira, Guido Araujo
The speed-up over an Im2Col + BLAS method based on current BLAS implementations for end-to-end machine-learning model inference is in the range of 9% - 25% for Intel x86 and 10% - 42% for IBM POWER10 architectures.
1 code implementation • 28 Jul 2022 • Martim Sousa, Ana Maria Tomé, José Moreira
This paper introduces a novel model-agnostic algorithm called adaptive ensemble batch multi-input multi-output conformalized quantile regression (AEnbMIMOCQR} that enables forecasters to generate multi-step ahead prediction intervals for a fixed pre-specified miscoverage rate in a distribution-free manner.
no code implementations • 6 Jul 2022 • Martim Sousa, Ana Maria Tomé, José Moreira
To show that this improved version outperforms the classic version of conformalized quantile regression and is more adaptive to heteroscedasticity, we extensively compare the prediction intervals of both in open datasets.
no code implementations • 9 Aug 2017 • Jeremy Kepner, Manoj Kumar, José Moreira, Pratap Pattnaik, Mauricio Serrano, Henry Tufo
The performance of the GraphBLAS implementation is measured relative to a standard dense linear algebra library implementation.