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.
A new algorithm POGO optimizes thousands of orthogonal matrices efficiently.
TorchKM: A GPU-Oriented Library for Kernel Learning and Model Selection
On-device inference of machine learning models for mobile phones is desirable due to its lower latency and increased privacy. Running such a compute-intensive task solely on the mobile CPU, however, can be difficult due to limited computing power, thermal constraints, and energy consumption. App developers and research…
Nested Slice Sampling accelerates Nested Sampling for GPU acceleration.
New theory maps neural network weights to optimize faster and scale.
This paper develops optimal transport methods on the roto-translation group SE2.
New formulations for comparing metric measure spaces with arbitrary positive measures.
Power-SMC reduces inference latency for training-free LLM reasoning.
BDH model learns like the brain, rivaling Transformer performance.