arXiv:2603. 05691v3 Announce Type: replace Abstract: It is increasingly common in machine learning to use learned models to label data and then employ such data to train more capable models.
arXiv:2609.38011v1 Announce Type: new Abstract: Modern machine learning systems are trained on mixtures of data from different domains, and choosing the right mixture can substantially improve downst...
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.
arXiv:2603.02069v2 Announce Type: replace Abstract: We study scaling laws of signSGD under a power-law random features (PLRF) model that accounts for both feature and target decay. We analyze the pop...
arXiv:2607. 15450v1 Announce Type: cross Abstract: Self-distillation (SD) is typically studied when the student is retrained on the teacher's original training inputs.
arXiv:2601. 19791v4 Announce Type: replace Abstract: We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting.
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: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.
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.
arXiv:2509. 17251v2 Announce Type: replace-cross Abstract: Existing theory suggests that for linear regression problems categorized by capacity and source conditions, gradient descent (GD) is always minimax optimal, while both ridge regression and online stochastic gradient descent (SGD) are polynomially suboptimal for certain categories of such problems.
arXiv:2608. 28564v1 Announce Type: cross Abstract: We study kernel ridge regression under anisotropic Gaussian data, where the input covariance decays as a power law with exponent $\alpha\geq 0$ for polynomial inner-product kernels.
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.
arXiv:2606. 01292v1 Announce Type: cross Abstract: Teacher-Student Knowledge Transfer (KT) is ubiquitous in modern machine learning, ranging from classical model compression via Knowledge Distillation (KD) to the emergent phenomenon of Weak-to-Strong (W2S) generalization.