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.
DDN dynamically combines weights for domain-specific models, improving performance.
New graph embedding method uses domain-specific knowledge.
Combining logic and probability has been a long stand- ing goal of AI research. Markov Logic Networks (MLNs) achieve this by attaching weights to formulas in first-order logic, and can be seen as templates for constructing features for ground Markov networks. Most techniques for learning weights of MLNs are domain-size…
Algorithm improves model performance on shifted concepts without retraining.
Paper proposes a novel approach to improve temporal clustering of time series data.
Develops a tensor network framework to reduce RNN complexity for high-dimensional sequence modeling.
Advanced kernels improve Gaussian process accuracy by incorporating domain knowledge.
Stock selection improved with a novel neural model capturing continuous stock dynamics.
GRTR framework uses graph regularization to improve financial forecasting.
This paper evaluates LLMs for technical market analysis, finding GPT-4 Turbo and FinGPT outperform passive benchmarks.
SX-GeoTree improves spatially coherent explanations in geospatial regression trees.
Predict missing and future data points in light curves using scalable Gaussian Processes.
Novel parallel GNN predicts protein-ligand interactions with high accuracy.