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

Somak Laha

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Stats Theory×1ML×1Stats ML×1

Frequent co-authors

Kevin Han Huang1×
Haoyu Ye1×
Morgane Austern1×

Research Timeline

2026
The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized Regression

This paper derives deterministic equivalents for the prediction risk of over-parameterized linear regression with degenerate covariance matrices and dependent covariates, and identifies the configurations at which the variance becomes singular using maximum matchings and the Dulmage--Mendelsohn decomposition.

Highlighted terms show continued research focus across papers

Papers

math.STcs.LGstat.MLTheoreticalRecentJul 27, 2026

The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized Regression

Kevin Han Huang, Haoyu Ye, Somak Laha, Morgane Austern

This paper derives deterministic equivalents for the prediction risk of over-parameterized linear regression with degenerate covariance matrices and dependent covariates, and identifies the configurat…

View →