Marco Ciccone

I am a Postdoctoral Fellow at Vector Institute in Toronto working with Colin Raffel.

Before, I was an ELLIS Postdoctoral Researcher at Politecnico di Torino and University College London (UCL).
I received my Ph.D. in Computer Science at Politecnico di Milano advised by Prof. Matteo Matteucci and Jonathan Masci working on iterative and conditional computation for visual models.
During my Ph.D., I was also a research intern at NVIDIA and NNAISENSE.
Previously, I proudly worked at the development of Horus.

I was Competition Track co-chair at NeurIPS in 2021, 2022 and 2023.

Research Interests

My research agenda is based on three pillars:

Decentralized Learning: to enable collaboration across users and sharing knowledge while preserving privacy and distributing computational efforts.
Continual Learning: to enable continuous knowledge integration allowing models to keep improving without forgetting previously acquired skills, unless on purpose.
Modular Learning: for creating models that are more reusable, efficient, and maintainable.

You can read more about my vision for the future of machine learning systems in my research statement.

Personal

In my spare time, I practice yoga, read novels, and play guitar. When I need to relax, I cook. When I'm not lazy, I go hiking and trekking. When I am sad or happy, I sing. When I can, I travel the world to learn about new cultures.

If you want to discuss anything or just connect, please drop me an email or reach me on Twitter or Linkedin!