ScalableHD speeds up hyperdimensional computing inference on multi-core CPUs by up to 10x (and up to ~18x in tables) over the TorchHD baseline while keeping the same model and accuracy.
Advancing hyperdimensional computing based on trainable encoding and adaptive training for efficient and accurate learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
ScalableHD: Scalable and High-Throughput Hyperdimensional Computing Inference on Multi-Core CPUs
ScalableHD speeds up hyperdimensional computing inference on multi-core CPUs by up to 10x (and up to ~18x in tables) over the TorchHD baseline while keeping the same model and accuracy.