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 approach stabilizes GANs by leveraging implicit competitive regularization.
This paper extends Mirror Descent to Riemannian manifolds for optimization.
Replication confirms CGD's effectiveness in competitive games.
The present paper considers if the new proposed conformal geometrodynamics (CGD) can extend the Nature features compared with general theory of relativity (GTR). The answer for this question can be connected with unique phenomenon arising from Riemann space transition used in GTR, to Weyl space used in CGD. We have in …
CGD improves diffusion models' out-of-distribution generalization.
Paper presents a semi-supervised grasp detection method using VQ-VAE.
SVDD and Deep SVDD improve radar target detection in clutter.