On-device research index

arXiv research

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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “Cross-training”

"It Looks All the Same to Me": Cross-index Training for Long-term Financial Series Predictionq-fin.ST

Study examines cross-training neural networks for financial index prediction.

problem Predicting financial indexes from different markets using machine learning.

method Investigated various neural network architectures and trained them on one market index to predict another.

result Cross-training models on one market index improved prediction accuracy for another market index.

Machine Learning Financial Indexes Artificial Neural Networks Cross-training Efficient Market Hypothesis

2025-11-11abs ↗pdf ↗

Residual Reweighted Conformal Prediction for Graph Neural Networkscs.LG

RR-GNN improves GNN prediction intervals by accounting for graph heteroscedasticity and structural biases.

problem Uncertainty quantification in GNNs for high-stakes domains.

method Graph-Structured Mondrian CP, Residual-Adaptive Nonconformity Scores, Cross-Training Protocol.

result Improved efficiency and no loss of coverage compared to CP baselines.

Graph Neural Networks Conformal Prediction Graph Heteroscedasticity Residual Reweighting Cross-Training

2025-06-09abs ↗pdf ↗

How does Disagreement Help Generalization against Label Corruption?cs.LG

Learning with noisy labels is one of the hottest problems in weakly-supervised learning. Based on memorization effects of deep neural networks, training on small-loss instances becomes very promising for handling noisy labels. This fosters the state-of-the-art approach "Co-teaching" that cross-trains two deep neural ne…

2019-01-14abs ↗pdf ↗

Adaptive Name Entity Recognition under Highly Unbalanced Datacs.CL

Improved NER performance on imbalanced data.

problem Highly unbalanced training data in NER tasks.

method Adapted a neural architecture with CRF and BI-LSTM layers, using pre-trained embeddings. Introduced a two-class split to optimize performance.

result Significant improvement in performance for weak classes with minimal training data.

Named Entity Recognition NER Unbalanced Data Conditional Random Field Bi-directional LSTM

2020-03-10abs ↗pdf ↗