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 algorithm reconstructs genealogies from genetic data.
Neural networks improve cancer risk prediction from family history data.
Gradient boosting enhances existing Mendelian models for genetic disease risk prediction.
Consider a Bayesian inference problem where a variable of interest does not take values in a Euclidean space. These "non-standard" data structures are in reality fairly common. They are frequently used in problems involving latent discrete factor models, networks, and domain specific problems such as sequence alignment…
Deep learning predicts crop yield integrating genotype and weather data.