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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “GFIM”

NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learningmath.OC

NG+ method improves deep learning efficiency and accuracy.

problem Efficiency and accuracy in deep learning models.

method Proposes NG+ method using matrix-product natural gradient approach.

result Established global convergence and provided regret bound.

deep learning natural gradient matrix-product fisher information global convergence

2021-06-14abs ↗pdf ↗

HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimationcs.LG

HyperINF improves influence function estimation for large models with better accuracy and efficiency.

problem Inaccurate and computationally expensive influence function estimation for large-scale models.

method HyperINF leverages Schulz's iterative algorithm and GFIM for low-rank approximation of Hessian matrix.

result HyperINF achieves superior accuracy and performance compared to existing methods on LoRA-tuned models.

influence function large-scale models Schulz's method GFIM matrix approximation

2024-10-07abs ↗pdf ↗