PaPi parallel integrator speeds neuro-spectral PDE learning
Experiments report up to two orders of magnitude faster training and inference, with some low-dimensional PDE runs under one second.
Stories per day · 30 days
Relatedfft1kernel-methods1neuro-spectral1pde1pinn1quasi-monte-carlo1rank-1-lattice1scientific-ml1softmax-attention1
2 stories, newest first · one card per story
Stories tagged #numerical-integration
Subgroup Rank-1 Lattice for Practical High-dimensional Black-box Integral Approximation
A subgroup rank-1 lattice method speeds high-dimensional black-box integral estimates, including softmax attention, via FFT correlations.