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.
ManifoldMind uses adaptive-curvature probabilistic spheres for trustworthy recommendations in semantic hierarchies.
This work improves data reconstruction methods by ensuring unique solutions and refining optimization.
EpiMer merges models by solving Fréchet mean on a Riemannian manifold.
New method discovers mean and variance causal graphs from heteroscedastic data.
This paper analyzes tokenized U.S. Treasuries, revealing patterns and roles in blockchain transactions.
The paper refines classical covariance asymptotics using geometric information geometry.
A lightweight framework improves convergence and stability of PINNs for complex PDEs.
New method accelerates neural network training by focusing on flat directions.
Study shows how to balance memory and learning efficiency in continual learning.
The Gauss-Newton method is analyzed for neural networks using Riemannian optimization techniques.
Geometrically refines Cramér-Rao bound using extrinsic manifold curvature.
The paper introduces heterogeneous manifolds for better graph embeddings.
Unified geometric interpretation of statistical estimation inequalities.
MCBP detects boundaries in high-dimensional data using curvature.