Reproduce “High-Dimensional Feature Selection by Feature-Wise Kernelized Lasso” 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
Makoto Yamada, Wittawat Jitkrittum, Leonid Sigal, Eric P. Xing, Masashi Sugiyama
HSIC Lasso selects a sparse set of features for prediction by matching output similarity patterns with a nonnegative combination of feature similarity patterns, allowing nonlinear relationships. On PIX10P, 50 features achieved accuracy .964 versus .920 for greedy FHSIC over 100 random 80/20 splits. Results favored it on four image datasets, were comparable on microarrays, and cKTA scored higher on TOX.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.