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...
By Diyuan Wu, Lehan Chen, Theodor Misiakiewicz, Marco Mondelli
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.
By Diyuan Wu, Lehan Chen, Theodor Misiakiewicz, Marco Mondelli
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:2412. 18081v3 Announce Type: replace-cross Abstract: We study Heterogeneous Transfer Learning (HTL) for high-dimensional regression with differing feature sets.
By Jae Ho Chang, Massimiliano Russo, Subhadeep Paul
arXiv:2502. 11665v3 Announce Type: replace-cross Abstract: The classical kernel ridge regression problem aims to find the best fit for the output $Y$ as a function of the input data $X\in \mathbb{R}^d$, with a fixed choice of regularization term imposed by a given choice of a reproducing kernel Hilbert space, such as a Sobolev space.
By Yang Li, Feng Ruan
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.
By Wendao Wu, Fangqing Zhang, Haihan Zhang, Cong Fang