'Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization', by Yaoyu Zhang, Leyang Zhang, Zhongwang Zhang, Zhiwei Bai.

http://jmlr.org/papers/v26/24-0192.html

#overparameterization #overparameterized #deep

Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization

'Overparametrized Multi-layer Neural Networks: Uniform Concentration of Neural Tangent Kernel and Convergence of Stochastic Gradient Descent', by Jiaming Xu, Hanjing Zhu.

http://jmlr.org/papers/v25/23-0740.html

#overparameterized #layers #neurons

Overparametrized Multi-layer Neural Networks: Uniform Concentration of Neural Tangent Kernel and Convergence of Stochastic Gradient Descent

'The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective', by Chi-Heng Lin, Chiraag Kaushik, Eva L. Dyer, Vidya Muthukumar.

http://jmlr.org/papers/v25/22-1312.html

#regularization #overparameterized #augmentation

The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective

'Benign Overfitting of Constant-Stepsize SGD for Linear Regression', by Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade.

http://jmlr.org/papers/v24/21-1297.html

#overfitting #overparameterized #sgd

Benign Overfitting of Constant-Stepsize SGD for Linear Regression

'Bagging in overparameterized learning: Risk characterization and risk monotonization', by Pratik Patil, Jin-Hong Du, Arun Kumar Kuchibhotla.

http://jmlr.org/papers/v24/23-0887.html

#bagging #overparameterized #prediction

Bagging in overparameterized learning: Risk characterization and risk monotonization

'Revisiting minimum description length complexity in overparameterized models', by Raaz Dwivedi, Chandan Singh, Bin Yu, Martin Wainwright.

http://jmlr.org/papers/v24/21-1133.html

#overparameterized #complexity #generalization

Revisiting minimum description length complexity in overparameterized models

'Benign overfitting in ridge regression', by Alexander Tsigler, Peter L. Bartlett.

http://jmlr.org/papers/v24/22-1398.html

#overparameterized #overfitting #ridge

Benign overfitting in ridge regression

Deep Double Descent via Smooth Interpolation

Matteo Gamba, Erik Englesson, Mårten Björkman, Hossein Azizpour

https://openreview.net/forum?id=fempQstMbV

#interpolated #deep #overparameterized

Deep Double Descent via Smooth Interpolation

The ability of overparameterized deep networks to interpolate noisy data, while at the same time showing good generalization performance, has been recently characterized in terms of the double...

OpenReview

Distributed SGD in overparameterized Linear Regression

https://openreview.net/forum?id=sfrcfYMOnZ

#sgd #overparameterized #distributed

Distributed SGD in overparameterized Linear Regression

We consider distributed learning using constant stepsize SGD over several devices, each sending a final model update to a central server. In a final step, the local estimates are aggregated. We...

OpenReview

'Foolish Crowds Support Benign Overfitting', by Niladri S. Chatterji, Philip M. Long.

http://jmlr.org/papers/v23/21-1199.html

#overparameterized #sparse #overfitting

Foolish Crowds Support Benign Overfitting