The paper studies a variant of stochastic gradient descent called SGDIR, which incorporates initial regularization. It derives dimension‑free upper bounds on the expected excess risk for the squared loss, providing new rates for both averaged and non‑averaged SGDIR under various assumptions. The authors also establish matching lower bounds in certain regimes and compare SGDIR to ridge regression in noisy settings, showing comparable performance up to a polylogarithmic factor.
By Nabil Kahal\'e
arXiv:2609.39440v1 Announce Type: new
Abstract: We compare the instance-wise, finite-sample risks of monotone spectral filters for linear regression, a broad class of estimators including principal c...
By Juno Kim, Hengyu Fu, Peter Bartlett, Jason D. Lee, Jingfeng Wu
arXiv:2406. 04425v2 Announce Type: replace Abstract: A fundamental problem in machine learning is understanding the effect of early stopping on the parameters obtained and the generalization capabilities of the model.
By Rishi Sonthalia, Jackie Lok, Elizaveta Rebrova
arXiv:2608. 02539v1 Announce Type: cross Abstract: We present a simple Gaussian approximation to the finite-sample distribution of the classical ridge regression estimator.
By Jos\'e Luis Montiel Olea, Ryan Strong, Amilcar Velez, Zhuoheng Xu, Haomin Yu
Conventional wisdom in deep learning holds that overparameterization---having more parameters $p$ than training samples $n$---is benign: larger models generalize better and, even without regularizatio...
arXiv:2309. 15769v3 Announce Type: replace-cross Abstract: Recent advances in deep learning have highlighted the phenomenon of benign overfitting in overparameterized statistical models, sparking significant interest in understanding its foundations.
By Dennis Shen, Dogyoon Song, Peng Ding, Jasjeet S. Sekhon
arXiv:2510. 12249v2 Announce Type: replace Abstract: In performative learning, the data distribution reacts to the deployed model - for example, because strategic users adapt their features to game it - which creates a more complex dynamic than in classical supervised learning.
By Edwige Cyffers, Alireza Mirrokni, Marco Mondelli
The paper investigates why diffusion models, unlike typical deep learning models, exhibit catastrophic overfitting when overparameterized. Through experiments on U‑Nets trained on CelebA and a random‑features theoretical analysis, it shows that the interpolation peak occurs at a model size proportional to the product of training samples and noise realizations, but the test loss starts to rise already at the number of samples, leading to memorization of the empirical score. Regularization techniques such as ridge penalties or early stopping can still make large models outperform smaller, unregularized ones.
By Rapha\"el Urfin, Tony Bonnaire, Giulio Biroli, Marc M\'ezard
arXiv:2607. 00207v1 Announce Type: cross Abstract: We develop a framework for analyzing the learning dynamics of $\ell_2$-adversarial training of single-index models on Gaussian mixtures in the high-dimensional limit under streaming stochastic gradient descent (SGD).
By Fabrizzio Sabelli
arXiv:2601. 19791v4 Announce Type: replace Abstract: We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting.
By Mingyue Xu, Gal Vardi, Itay Safran
arXiv:2601. 16041v2 Announce Type: replace-cross Abstract: In constrained stochastic optimization, one expects that restricting the feasible set, provided it still contains the true parameter, should not increase the statistical risk of the corresponding projection estimator.
By Omar Al-Ghattas
arXiv:2608. 07281v1 Announce Type: cross Abstract: This paper investigates the asymptotic behavior of the out-of-sample prediction risk of the high-dimensional ridgeless least-squares estimator when the feature dimension $p$ and the sample size $n$ grow proportionally.
By Zhijun Liu, Dandan Jiang