paper-with-me

홈 › Papers

Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression

2024-10-03 · Kai Tan, Pierre C. Bellec

This paper studies the generalization performance of iterates obtained by Gradient Descent (GD), Stochastic Gradient Descent (SGD) and their proximal variants in high-dimensional robust regression problems. The number of features is comparable to the sample size and errors may be heavy-tailed. We introduce estimators that precisely track the generalization error of the iterates along the trajectory of the iterative algorithm. These estimators are provably consistent under suitable conditions. The results are illustrated through several examples, including Huber regression, pseudo-Huber regression, and their penalized variants with non-smooth regularizer. We provide explicit generalization error estimates for iterates generated from GD and SGD, or from proximal SGD in the presence of a non-smooth regularizer. The proposed risk estimates serve as effective proxies for the actual generalization error, allowing us to determine the optimal stopping iteration that minimizes the generalization error. Extensive simulations confirm the effectiveness of the proposed generalization error estimates.

📄 PDF Abstract BibTeX arXiv:2410.02629

Code (1)

kaitan365/sgd-generlization-errors 공식 구현 pytorch

Tasks

regression

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Uncertainty quantification for iterative algorithms in linear models with application to early stopping

2024-04-27 · Pierre C. Bellec, Kai Tan

This paper investigates the iterates $\hbb^1,\dots,\hbb^T$ obtained from iterative algorithms in high-dimensional linear regression problems, in the regime where the feature dimension $p$ is comparable with the sample si…

Uncertainty Quantificationvalid

Trajectory Constraints for Imaging Inverse Problems

2026-05-27 · Chaoyan Huang, Haijie Yuan, Saiprasad Ravishankar arxiv

Diffusion-based and iterative methods have become effective tools for solving imaging inverse problems. Their reconstruction process naturally forms a trajectory of intermediate estimates. Although these intermediate est…

Image Reconstruction

CAPE: Context-Aware Diffusion Policy Via Proximal Mode Expansion for Collision Avoidance

2025-11-27 · Rui Heng Yang, Xuan Zhao, Leo Maxime Brunswic, Montgomery Alban 외 arxiv

In robotics, diffusion models can capture multi-modal trajectories from demonstrations, making them a transformative approach in imitation learning. However, achieving optimal performance following this regiment requires…

Collision Avoidance

Optimization dependent generalization bound for ReLU networks based on sensitivity in the tangent bundle

2023-10-26 · Dániel Rácz, Mihály Petreczky, András Csertán, Bálint Daróczy

Recent advances in deep learning have given us some very promising results on the generalization ability of deep neural networks, however literature still lacks a comprehensive theory explaining why heavily over-parametr…

Sensitivity

Tracking of Spatially Dynamic Room Impulse Responses Along Locally Linearized Trajectories

2025-06-13 · Kathleen MacWilliam, Thomas Dietzen, Toon van Waterschoot

Measuring room impulse responses (RIRs) at multiple spatial points is a time-consuming task, while simulations require detailed knowledge of the room's acoustic environment. In prior work, we proposed a method for estima…