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

3 results for “IHVP”

Better Training Data Attribution via Better Inverse Hessian-Vector Productscs.LG

ASTRA improves TDA by more accurately approximating iHVP.

problem Improving insights into training data attribution.

method ASTRA uses EKFAC-preconditioner on Neumann series iterations to accurately approximate iHVP.

result Improving iHVP approximation significantly improves TDA performance.

Training data attribution Inverse Hessian-Vector Product Gradient-based methods Neumann series EKFAC-preconditioner

2025-07-19abs ↗pdf ↗

Rethinking Influence Functions of Neural Networks in the Over-parameterized Regimecs.LG

Improves understanding of neural network predictions using influence functions.

problem Challenges in understanding neural network predictions.

method Utilized NTK theory to calculate influence functions for over-parameterized neural networks.

result Proved that the approximation error of IF can be arbitrarily small in the over-parameterized regime.

influence functions neural networks over-parameterized NTK theory Hessian-vector product

2021-12-15abs ↗pdf ↗

Studying Large Language Model Generalization with Influence Functionscs.LG

Influence functions help study large language model generalization, revealing surprising decay patterns.

problem Understanding and mitigating risks in large language models (LLMs).

method Eigenvalue-corrected Kronecker-Factored Approximation (EK-FAC) to scale influence functions to LLMs.

result Influences decay to near-zero when key phrases order is flipped, revealing a surprising limitation.

large language models influence functions generalization IHVP TF-IDF

2023-08-07abs ↗pdf ↗