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 study improves sentence embeddings from BERT models.
This work characterizes how data augmentation shapes neural representations.
Statistical characteristics of deep network representations, such as sparsity and correlation, are known to be relevant to the performance and interpretability of deep learning. When a statistical characteristic is desired, often an adequate regularizer can be designed and applied during the training phase. Typically, …
SVarM uses varifold representations for shape classification and regression.
VAIOM models financial returns using continuous input and categorical output.