Reproduce “Gradient Boosting for Efficient Rank Discovery in Tensor Network Kernel Machines” 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
Albert Saiapin, Kim Batselier
GB-CPKM adds fixed-rank CP kernel-machine learners trained on residuals and uses validation performance to choose when to stop. On the Precipitation benchmark, it reports test MSE 0.9454 ± 0.04 versus 0.9419 ± 0.04 for cross-validation rank search, training time 8.35 ± 1.05 versus 88.59 ± 11.84 seconds, and peak memory 1,156 versus 2,885 MiB. These benchmark results do not establish equivalence or general superiority.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.