Google’s H-Transformer-1D: Fast One-Dimensional Hierarchical Attention With Linear Complexity for Long Sequence Processing | Synced

A Google Research team draws inspiration from two numerical analysis methods — Hierarchical Matrix (H-Matrix) and Multigrid — to address the quadratic complexity problem of attention mechanisms in ...

By · · 1 min read

Source: Synced | AI Technology & Industry Review

A Google Research team draws inspiration from two numerical analysis methods — Hierarchical Matrix (H-Matrix) and Multigrid — to address the quadratic complexity problem of attention mechanisms in transformer architectures, proposing a hierarchical attention scheme that has linear complexity in run time and memory.