On the Benefits of Over-parameterization for Out-of-Distribution
Generalization

On the Benefits of Over-parameterization for Out-of-Distribution Generalization

26 March 2024

Yong Lin

Tong Zhang

ArXiv (abs)PDF HTML

Papers citing "On the Benefits of Over-parameterization for Out-of-Distribution Generalization"

5 / 5 papers shown

Title
Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods Yifan Hao Xingyuan Pan Hanning Zhang Chenlu Ye Boyao Wang Tong Zhang 232 3 0 02 Jun 2025
Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the role of model complexity Mouin Ben Ammar David Brellmann Arturo Mendoza Antoine Manzanera Gianni Franchi OODD 324 0 0 04 Nov 2024
Theoretical Limitations of Ensembles in the Age of Overparameterization Niclas Dern John P. Cunningham Geoff Pleiss BDL UQCV 295 2 0 21 Oct 2024
Scalable Ensemble Diversification for OOD Generalization and Detection Alexander Rubinstein Luca Scimeca Damien Teney Seong Joon Oh BDL OOD 994 2 0 25 Sep 2024
Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling Cristian Rodriguez-Opazo Ehsan Abbasnejad Damien Teney Edison Marrese-Taylor Hamed Damirchi Anton Van Den Hengel VLM 310 1 0 27 May 2024