arXiv Machine Learning July 9, 2026 By Haotian Lin, Matthew Reimherr

Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer

Read the original on arXiv Machine Learning →

arXiv:2501. 10870v2 Announce Type: replace-cross Abstract: The principal objective of this work is twofold within nonparametric regression settings: (1) to establish the minimax optimal convergence rates for fixed-bandwidth Gaussian kernel spectral algorithms when the true regression function resides in a Sobolev space, and (2) to apply Gaussian spectral algorithms for achieving robust and adaptive transfer learning under concept shift.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

fine-tuning

arXiv Machine Learning

Jul 21

Spectral-Transport Stability and Benign Overfitting in Interpolating Learning

arXiv:2604. 08625v2 Announce Type: replace-cross Abstract: We develop a theoretical framework for generalization in the interpolating regime of statistical learning.

By Gustav Olaf Yunus Laitinen-Lundstr\"om Fredriksson-Imanov

safety

arXiv AI

Jun 2

What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression

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

efficiency

arXiv Machine Learning

Jul 7

SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity

arXiv:2607. 04189v1 Announce Type: new Abstract: Federated Learning (FL) is fundamentally challenged by statistical heterogeneity, where non-identically distributed (non-IID) data induces client drift that severely hampers global convergence.

By Liyang Yuan, Yibo Yang, Dandan Guo, Peter Richtarik, Zhouchen Lin

benchmarks safety

arXiv AI

Jun 16

ALCL: An Adaptive Log-Correntropy Loss for Robust Learning under Non-Gaussian Noise

arXiv:2606. 16050v1 Announce Type: cross Abstract: Robust deep learning under heavy-tailed and impulsive noise remains challenging because conventional losses such as mean squared error (MSE) exhibit unbounded sensitivity to outliers.

By Mainak Kundu, Ria Kanjilal, Ismail Uysal

benchmarks

arXiv Machine Learning

Jun 30

Generalization error of min-norm interpolators in transfer learning

arXiv:2406. 13944v2 Announce Type: replace-cross Abstract: This paper establishes the generalization error of pooled min-$\ell_2$-norm interpolation in transfer learning, where data from diverse distributions are available.

By Yanke Song, Kenneth Gu, Sohom Bhattacharya, Pragya Sur

fine-tuning safety

arXiv Machine Learning

Jul 30

Minimax-Optimal Generalization Bounds for Smooth Deep Neural Networks Trained by (Stochastic) Gradient Descent

arXiv:2606. 06772v2 Announce Type: replace-cross Abstract: Characterizing the optimization dynamics and statistical performance of over-parameterized deep neural networks (DNNs) remains a central challenge in understanding the remarkable success of deep learning.

By Junyu Zhou, Puyu Wang, Dennis Wagner, Yunwen Lei, Marius Kloft, Yiming Ying

Related stories

Spectral-Transport Stability and Benign Overfitting in Interpolating Learning

What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression

SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity

ALCL: An Adaptive Log-Correntropy Loss for Robust Learning under Non-Gaussian Noise

Generalization error of min-norm interpolators in transfer learning

Minimax-Optimal Generalization Bounds for Smooth Deep Neural Networks Trained by (Stochastic) Gradient Descent