A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New method corrects output-side domain shift without labeled data.
We study the problem of learning high dimensional regression models regularized by a structured-sparsity-inducing penalty that encodes prior structural information on either input or output sides. We consider two widely adopted types of such penalties as our motivating examples: 1) overlapping group lasso penalty, base…
iSTFTNet speeds up mel-spectrogram vocoders without sacrificing quality.
Bayesian brain computes without noise, using correlated activity.