Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jake Zummo

Jake Zummo

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Stats ML×2ML×2Stats Theory×1

Frequent co-authors

Younghun Lee2×
Wei Biao Wu2×

Research Timeline

2026
A Nonlinear Time-Series Theory for Constant-step SGD with Momentum

The paper studies the stationary behavior and distributional limits of constant-step stochastic gradient descent with momentum (SGDM) as a nonlinear time series.

Limit Theory for Online Expectile Estimation under Short and Long Range Dependence

The paper develops a one-pass stochastic-gradient algorithm for online estimation of expectiles from dependent data.

Highlighted terms show continued research focus across papers

Papers

stat.MLcs.LGTheoreticalRecentOct 12, 2026

A Nonlinear Time-Series Theory for Constant-step SGD with Momentum

Younghun Lee, Jake Zummo, Wei Biao Wu

The paper studies the stationary behavior and distributional limits of constant-step stochastic gradient descent with momentum (SGDM) as a nonlinear time series.

View →
stat.MLcs.LGmath.STEmpirical
Recent
Oct 12, 2026

Limit Theory for Online Expectile Estimation under Short and Long Range Dependence

Younghun Lee, Jake Zummo, Wei Biao Wu

The paper develops a one-pass stochastic-gradient algorithm for online estimation of expectiles from dependent data.

View →