Aurélien Lucchi

works on

convergence analysis 1 convex optimization 1 federated learning 1 heterogeneous data 1 local sgd 1 second-order heterogeneity 1

From the 1 of 24 linked papers with an AI index.

activity

20242026

collaborators

Showing stat.MLShow all

1 paper · 1 filter

stat.ML2025

Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters

Anastasis Kratsios, Tin Sum Cheng, Aurelien Lucchi +1

Low-Rank Adaptation (LoRA) has emerged as a widely adopted parameter-efficient fine-tuning (PEFT) technique for foundation models. Recent work has highlighted an inherent asymmetry…