Reproduce “Superposed Inference for Hyperdimensional Computing” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Quanling Zhao, Nilesh Prasad Pandey, Ye Tian, Tajana Rosing
SupHDC combines K keyed queries before a nonlinear random-Fourier-feature HDC projection, then uses slot-specific prototype banks to classify each query and margin-gated fallback to re-encode uncertain cases. Across ten datasets at full precision and D=10,000, K=2 achieved 1.39× analytical speedup with +0.37 percentage points mean accuracy change; K=4 achieved 2.08× with −2.67 points. These are not wall-clock results.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.