When is Fine-Tuning Scalable? Certified Recovery from Noisy Data and Linear-Cost Fine-Tuning on Structured Task Shifts

arXiv:2509.00924 · stat.ML, cs.LG, cs.NA, cs.NE, math.NA, math.PR · Submitted 2025-08-31 · Read on arXiv

stat.ML, cs.LG, cs.NA, cs.NE, math.NA, math.PR

Submitted: 2025-08-31

Updated: 2026-10-26

Terminology

• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Scalable Posterior Uncertainty for Flexible Density-Based Clustering
• A Transport Geometry of Benign Overfitting
• Efficient quadratic entropy with distance sketches