Andrea Paudice
 |
Assistant Professor (Tenure Track) |
About me
I am assistant professor (tenure track) at the Department of Computer science of Aarhus University, where I'm part of the Algorithms, Data, and Artificial Intelligence section.
Prior to this, I was a postdoctoral researcher at the University of Milan, Italy. I worked among the LAILA team led by Nicolò Cesa-Bianchi.
I obtained my PhD from the University of Milan, under the supervision of Nicolò Cesa-Bianchi and Massimiliano Pontil.
You can find more about my background on my LinkedIn.Research Interests
My recent research interests revolve around the theoretical foundations of machine learning with emphasis on the impact of heavy-tailed noise.
More precisely my interests spans the following topics:
Stochastic optimization
Statistical learning theory and concentration inequalities
Applications to adversarial learning and computer security
My list of publications is available on my Google Scholar.
If you are interested in working with me feel free to drop me an email!
Awards
Jan. 2026: I have received the Villum Young Investigator award (10.2 million DKK / 1.4 million euros) for the project “Robustness to Noise in Machine Learning”. Thanks to Villum Fonden!
Nov. 2024: I have received the Novo Nordisk Starting Grant award (3 million DKK / 400000 euros) for the project “Actionable Performance Guarantees in Machine Learning”. Thanks to Novo Nordisk foundation!
Openings
I currently have several open postdoctoral and PhD positions in stochastic optimization and generalization bounds. If you have a strong mathematical background (and a good research record for postdoctoral applications) and are interested, feel free to email me with a brief description of your interests and your CV.
News
Jan. 2026: our work "Sample-Near-Optimal Agnostic Boosting with Improved Running Time" on improving the runtime of near-optimal agnostic boosting got accepted at ALT (joint work with A. da Cunha, and M.M. Høgsgaard)!
Sep. 2025: our work "Revisiting Agnostic Boosting" on statistical near-optimal agnostic boosting got accepted at NeurIPS (joint work with A. da Cunha, M.M. Høgsgaard, and Y. Sun)!
May 2025: our work "Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means" on uniform convergence under for heavy-tailed data got accepted at ICML (joint work with M.M. Høgsgaard)!