… an algorithm for personalized FL (pFedMe) using Moreau envelopes as … personalized
model optimization from the global model learning in a bi-level problem stylized for personalized …

… on federated learning [11], [12] The research on federated learning … federated learning,
personalization was proposed by various researchers to be implemented into distributed learning…

… In Chapter 2, we will discuss the powerful use cases of federated learning to provide a … in
the field of federated learning, specifically: the original form of federated learning, penalization, …

… In this section, we propose a personalization approach for federated learning and analyze
its statistical properties. Following the statistical learning theory, in a federated learning setting …

… work with Moreau envelope based on ADMM for training models. … Here, we present the
definition of the Moreau envelope. … Next, we describe a useful property of Moreau envelope [38]. …

… [Citation13] present pFedMe algorithm for PFL via adopting a different formulation for
personalization, namely Moreau Envelopes (ME). The proposed algorithm is a joint bi-level …

… In the context of personalized federated learning (FL), the critical challenge is to balance …
-aware personalized FL method where each client can automatically balance the training of its …

… Note that Φρ is a smooth function known as the Moreau envelope of φ. By choosing φ to be
the l2 norm, we obtain a (1/ρ)-smooth approximation of the geometric median aggregation as …

… Federated composite optimization (FCO) is an optimization problem in federated learning …
For pFedMe, the local model is constructed based on the Moreau envelope of fi, namely, …

… We formulate the personalized federated learning problem as follows, studying it under the
lens of stochastic optimization [5]. Consider N ∈ N∗ agents denoted by integers 1 ⩽ i ⩽ N, …