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.
This paper uses group theory to create data-free, feature-free clustering.
Deep learning matches classical feature-based AS models for TSP.
Auto-sklearn 2.0 simplifies AutoML with meta-learning and meta-feature-free techniques.
Poisson plane and sphere --- homogeneous spaces of Poisson groups E(2) and SU(2) (resp.) --- have phase spaces (corresponding symplectic groupoids), in which a free Hamiltonian is naturally defined. We solve the equations of motion and point out some unexpected features: free motion on the plane is bounded (periodic) a…
FFRK automatically extracts features for spatial interpolation without external variables.
Interleaved RNNs detect fraud without costly features.
Develops deep learning models for choice modeling.
Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired training data and learning discriminative identity-sensitive and view-invariant features in the presence of large pose variations. In this work, we address both problems by proposing a novel deep person image generation model for…