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 “super-acceleration”

Gradient descent with momentum --- to accelerate or to super-accelerate?cs.LG

Super-acceleration of gradient descent with momentum improves loss function minimization.

problem Minimizing loss functions in machine learning.

method Extending Nesterov acceleration by using gradients at multiple steps ahead.

result Super-acceleration of the momentum algorithm is beneficial for various loss landscapes and tasks.

gradient descent momentum Nesterov acceleration super-acceleration machine learning

2020-01-17abs ↗pdf ↗

Transfer Learning for Nonparametric Regression: Non-asymptotic Minimax Analysis and Adaptive Procedurestat.ML

New estimator achieves minimax optimal risk in transfer learning.

problem Nonparametric regression with transfer learning.

method Confidence thresholding estimator and data-driven adaptive algorithm.

result Adaptive algorithm achieves minimax risk up to a logarithmic factor.

transfer learning nonparametric regression minimax risk adaptive procedure auto-smoothing

2024-01-22abs ↗pdf ↗