Gabriel Arpino

Doctoral Student

University of Cambridge

Biography

I am a third year PhD student at the University of Cambridge working with Prof. Ramji Venkataramanan. I am grateful to be generously supported by the Cambridge Trust.

Previously, I completed my Master’s degree in EEIT at ETH Zürich, advised by Prof. Afonso Bandeira. Before that, I completed my undergraduate degree in Engineering Science at the University of Toronto, where I worked with Prof. Daniel Roy.

My academic interests lie in the areas of statistical machine learning, applied probability, information theory, optimization, and computation.

Publications

Gabriel Arpino, Xiaoqi Liu, Ramji Venkataramanan (2024). Inferring Change Points in High-Dimensional Linear Regression via Approximate Message Passing. In International Conference on Machine Learning (ICML), 2024.

Preprint

Gabriel Arpino, Daniil Dmitriev, Nicolo Grometto (2023). Greedy Heuristics and Linear Relaxations for the Random Hitting Set Problem. (alphabetical order).

Preprint

Gabriel Arpino, Ramji Venkataramanan (2023). Statistical-Computational Tradeoffs in Mixed Sparse Linear Regression. In Conference on Learning Theory (COLT), 2023.

Preprint Source Document

Freya Behrens, Gabriel Arpino, Yaroslav Kivva, Lenka Zdeborová (2022). (Dis)assortative partitions on random regular graphs. In Journal of Physics A: Mathematical and Theoretical.

Source Document

*Gabriel Arpino, *Nicolò Grometto, Afonso Bandeira (2020). Group Testing in the High Dilution Regime. Asterisk denotes equal contribution. In 2021 IEEE International Symposium on Information Theory (ISIT).

Preprint Code Source Document

Gintare Karolina Dziugaite, Kyle Hsu, Waseem Gharbieh, Gabriel Arpino, Daniel M. Roy (2020). On the role of data in PAC-Bayes bounds. In 2021 International Conference on Artificial Intelligence and Statistics (AISTATS).

Preprint Source Document

Gintare Karolina Dziugaite, Gabriel Arpino, Daniel Roy (2018). Towards generalization guarantees for SGD: Data-dependent PAC-Bayes priors. In NeurIPS 2018 Workshop on Bayesian Deep Learning.

PDF Source Document

Gabriel Arpino, Kyle Morris, Sasanka Nagavalli, Katia Sycara (2018). Using Information Invariants to Compare Swarm Algorithms and General Multi-Robot Algorithms. In 2018 IEEE International Conference on Robotics and Automation (ICRA).

Preprint PDF Source Document

Kyle Morris, Gabriel Arpino, Sasanka Nagavalli, Katia Sycara (2017). Full Stack Swarm Architecture. In RISS 2017 Working Papers Journal.