Morgane Austern

Jul 2026

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

Over-parameterized linear regression has been widely studied over the last decade. However, most existing works assume that the covariates are independent and that their covariance matrices are non-degenerate. In this paper, we relax both assumptions and derive deterministic equivalents for the prediction risk in a van...

Kevin Han Huang, Haoyu Ye, Somak Laha et al. · arXiv.org · 0 citations

#artificial intelligence Preprint Sep 2026

Statistical attribute alignment for black-box generative AI via output post-processing

Experiments on text-to-image generation and geocoded persona generation tasks show that the post-processing algorithms improve statistical attribute alignment, complementing prompting-based interventions.

Kevin Jiang, Morgane Austern, Edgar Dobriban et al. · 0 citations

#data science Preprint Jul 2026

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

Over-parameterized linear regression has been widely studied over the last decade. However, most existing works assume that the covariates are independent and that their covariance matrices are non-degenerate. In this paper, we relax both assumptions and derive deterministic equivalents for the prediction risk in a van...

Kevin Han Huang, Haoyu Ye, Somak Laha et al. · 0 citations