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.
Paper shows attacks on transfer learning models without target-specific info.
TASFAR adapts regression models without labeled source data.
Recent years have demonstrated that using random feature maps can significantly decrease the training and testing times of kernel-based algorithms without significantly lowering their accuracy. Regrettably, because random features are target-agnostic, typically thousands of such features are necessary to achieve accept…
Efficient inference for adaptive data with directional stability condition.
Sharp theory of neural network scaling laws for hierarchical targets.
Bayesian approach selects features for a specific target with high confidence.