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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “input-magnitude”

Sharp Stability Threshold and Certification for Designing Stable Residual Architecturescs.LG

Sharp stability threshold found for deep residual architectures.

problem Ensuring stable training and inference in deep residual networks.

method Sublinear-growth principle and optimal-control analysis.

result Stable training condition: input-magnitude exponent q ≤ 1.

deep learning residual networks stability training input-magnitude

2026-07-16abs ↗pdf ↗

Accelerating Birkhoff Projection for Manifold-Constrained Hyper-Connectionscs.DC

Accelerates Birkhoff projection for manifold-constrained hyper-connections with high accuracy and speed.

problem Inaccurate and slow Birkhoff projection in mHC implementations.

method Dual formulation, Newton's method, implicit differentiation, warp-level CUDA kernel.

result Substantial speedups and accuracy improvements in doubly stochastic projections.

Birkhoff projection manifold-constrained hyper-connections Sinkhorn-Knopp iterations Newton's method CUDA acceleration

2026-05-26abs ↗pdf ↗

Forecasting the 2016-2017 Central Apennines Earthquake Sequence with a Neural Point Processphysics.geo-ph

Neural model outperforms ETAS in forecasting Central Apennines earthquakes.

problem Short-term seismicity forecasting with incomplete data.

method Extended a neural network model to the magnitude domain, using it to forecast earthquakes above a target magnitude threshold.

result Neural model outperforms ETAS at lower magnitude thresholds, due to its robustness to missing data.

neural networks seismicity forecasting earthquake sequence magnitude domain short-term forecasting

2023-01-24abs ↗pdf ↗