Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning

PubMed 2026 Open access

Read full text

Authors: Filip Kovačević, Hong Chang Ji, Denny C.-Y. Wu, Mahdi Soltanolkotabi, Marco Mondelli

DOI: 10.48550/arxiv.2602.02431

Cited by: 0

Abstract

gradient steps suffice to achieve strong (exact) recovery.

Stochastic Gradient Optimization Techniques Sparse and Compressive Sensing Techniques Machine Learning and Algorithms