activity
20242026
collaborators

8 papers

cs.LG2026

From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD

Christoph H. Lampert, Hossein Zakerinia

Understanding the relationship between generalization and privacy remains a central challenge in modern machine learning theory, particularly for deep networks trained by variants…

cs.LG2025

Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes

Hossein Zakerinia, Christoph H. Lampert

We present new fast-rate PAC-Bayesian generalization bounds for multi-task and meta-learning in the unbalanced setting, i.e. when the tasks have training sets of different sizes, a…

cs.LG2025

Communication-Efficient Federated Learning With Data and Client Heterogeneity

Hossein Zakerinia, Shayan Talaei, Giorgi Nadiradze +1

Federated Learning (FL) enables large-scale distributed training of machine learning models, while still allowing individual nodes to maintain data locally. However, executing FL a…

cs.LG2025

Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions

Hossein Zakerinia, Jonathan Scott, Christoph H. Lampert

Personalized federated learning has emerged as a popular approach to training on devices holding statistically heterogeneous data, known as clients. However, most existing approach…

cs.LG2025

From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning

Hossein Zakerinia, Dorsa Ghobadi, Christoph H. Lampert

Deep learning methods are known to generalize well from training to future data, even in an overparametrized regime, where they could easily overfit. One explanation for this pheno…

cs.LG2025

PeFLL: Personalized Federated Learning by Learning to Learn

Jonathan Scott, Hossein Zakerinia, Christoph H. Lampert

We present PeFLL, a new personalized federated learning algorithm that improves over the state-of-the-art in three aspects: 1) it produces more accurate models, especially in the l…