Richard Oliveira

Hello! My name is Richard, and I'm a Marie Skłodowska-Curie doctoral fellow and Phd candidate at Politecnico di Milano, Italy, in the department of Electronics, Information Technology, and Bioengineering (DEIB) and the department of Mathematics (DMAT), under the supervision of Dr. Stefano Savazzi. Furthermore, I am also affiliated with the Institute of Electronics, Computer and Telecommunication Engineering (IEIIT) at the Consiglio Nazionale delle Ricerche.

My background can be broadly defined as that of a Mathematical Engineer with a focus on developing mathematical models for how information is acquired, communicated and processed in engineered systems, with applications in control, computation and Machine Learning. My research investigates the mathematical foundations of machine learning from an optimization-theoretic perspective, with a focus on distributed and networked learning systems. I am particularly interested in the role of regularization in learning dynamics, including how implicit regularization arises naturally in collaborative estimation over graphs. My work aims to characterize how stability, convergence, and generalization of gradient-based algorithms are shaped by consensus mechanisms, network topology, and spectral properties of the communication graph.

I received my MSc. in Electrical Engineering, Signal and Image Processing and a BSc. in Electrical Engineering, Machine Learning and Controls from the Electrical and Computer Engineering Department at the University of California, San Diego, La Jolla, USA. During my MSc. studies I have worked on the theory of Discrete Pearson-Rayleigh Random Walks under the supervision of Prof. Massimo Franceschetti.