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

2 results for “HTSR”

Grokking and Generalization Collapse: Insights from \texttt{HTSR} theorycs.LG

Novel anti-grokking phase discovered in neural networks, revealed by HTSR layer quality metric.

problem Understanding and detecting overfitting in neural networks.

method 3-layer MLP, weight decay, HTSR layer quality metric

α

, correlation traps, Kolmogorov–Smirnov tests.

result Anti-grokking phase detected late in training, revealed by

α< 2

and correlation traps.

neural networks overfitting generalization anti-grokking HTSR

2025-06-04abs ↗pdf ↗

Beyond Accuracy: A Unified Random Matrix Theory Diagnostic Framework for Crash Classification Modelscs.LG

Unified framework detects overfitting in crash classification models.

problem Evaluation metrics fail to detect overfitting in crash classification models.

method Random Matrix Theory and Heavy-Tailed Self-Regularization framework applied to various model types.

result Power-law exponent α reliably distinguishes well-regularized from overfit models.

crash classification Random Matrix Theory overfitting spectral quality model selection

2026-02-23abs ↗pdf ↗