Developing machine learning models heavily relies on access to data. To build a
responsible data economy and protect data ownership, it is crucial to enable learning …

Heterogeneous federated learning without assuming any structure is challenging due to the
conflicts among non-identical data distributions of clients. In practice, clients often comprise …

Standard machine learning (ML) paradigms often operate within the confines of a single
controlled environment. The conventional approach involves gathering a centralized training …

Personalized federated learning (PFL) aims at learning personalized models for users in a
federated setup. We focus on the problem of privately estimating histograms (in the KL …

In the realm of multi-objective optimization, we introduce''Multi-objective multi-solution
Transport (MosT)'', a novel solution for optimizing multiple objectives that employs multiple …

Personalized federated learning (PFL) aims to leverage the collective wisdom of clients' data
while constructing customized models that are tailored to individual client's data …

Rozmiary róznych zbiorów danych gromadzonych na swiecie gwałtownie rosn a. Dane te sa
składowane w oddzielnych, niezaleznych lokalizacjach. Z tego powodu wzrasta liczba …

I am an MS student at Carnegie Mellon University working with Prof. Virginia Smith, Artur
Dubrawski, and Steven Wu. My research focuses on privacy-preserving machine learning …