2 papers
cs.CV2024
PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer
Pierre-David Letourneau, Manish Kumar Singh, Hsin-Pai Cheng +6
We present Polynomial Attention Drop-in Replacement (PADRe), a novel and unifying framework designed to replace the conventional self-attention mechanism in transformer models. Not…
math.NA2023
A Sparse Fast Chebyshev Transform for High-Dimensional Approximation
Dalton Jones, Pierre-David Letourneau, Matthew J. Morse +1
We present the Fast Chebyshev Transform (FCT), a fast, randomized algorithm to compute a Chebyshev approximation of functions in high-dimensions from the knowledge of the location…