General
On the Rate of Gaussian Approximation for Online Linear Regression Problems
arXiv stat.ML0 views
arXiv:2509.14039v2 Announce Type: replace Abstract: In this paper, we consider the problem of Gaussian approximation for the online linear regression task. We derive the corresponding rates for the setting of a constant stepsize and study the explicit dependence of the convergence rate on the problem dimension $d$ and quantities related to the design matrix. When the number of iterations $n$ is known in advance, our results yield a normal approximation rate of order $\sqrt{\log{n}/n}$, provided that the sample size $n$ is large enough.
Source：https://arxiv.org/abs/2509.14039PreviousSpectral and Subspace Dynamics of LoRA in Supervised Fine-Tuning and Reinforcement LearningNextVariational Estimators for Node Popularity Models
Related posts
Geometry-Aware Channel Aging in MIMO Systems: When Is Kronecker Separability Enough?
0arXiv eess.SP
A Particle-Based Multiuser Communication with a Budget Limit
0arXiv eess.SP
A Partial-Matching Proof of the Neyman--Pearson Lemma
0arXiv stat.TH
Modular Parameterized Model Checking of Threshold-Based Distributed Algorithms
0arXiv cs.DC
Information-Spectrum General Formulas for the Capacity Region of Classical-Quantum Multiple Access Channels
0arXiv math.IT
A State-of-the-Art Review of Computational Models for Analyzing Longitudinal Wearable Sensor Data in Healthcare
0arXiv cs.HC