Research
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
0111 · Jan 202019922001200920172026
3 results for “KGD”
Beyond Cross-Validation: Adaptive Parameter Selection for Kernel-Based Gradient Descentsstat.ML

Paper proposes adaptive parameter selection for KGD algorithms.

problem Improving parameter selection for kernel-based gradient descent.
method Integrates bias-variance analysis with splitting method, introduces empirical effective dimension.
result Adaptive parameter selection strategy achieves optimal generalization error bound.
kernel-based gradient descentadaptive parameter selectionlearning theoryintegral operatorbias-variance analysis
2026-03-03abs ↗pdf ↗
Adaptive Stopping Rule for Kernel-based Gradient Descent Algorithmscs.LG

Adaptive rule improves kernel-based gradient descent performance.

problem Improving convergence speed of kernel-based gradient descent algorithms.
method Empirical effective dimension for stopping rule, learning theory analysis, integral operator approach.
result Optimal learning rates and iteration bounds for KGD with adaptive stopping rule.
kernel-based gradient descentlearning theoryintegral operatorempirical effective dimensionearly stopping
2020-01-09abs ↗pdf ↗
A Computable Measure of Suboptimality for Entropy-Regularised Variational Objectivesstat.CO

A new measure helps compute suboptimality in entropy-regularized methods.

problem Computing suboptimality in entropy-regularized variational objectives when unnormalised densities are unavailable.
method Introduced 'kernel gradient discrepancy' (KGD) to compute suboptimality explicitly.
result KGD characterizes kernel Stein discrepancy (KSD) in the standard Bayesian context and measures variational gradient size.
gradient discrepancykernel gradient discrepancyKGDentropy-regularizedvariational objectives
2025-09-12abs ↗pdf ↗