Jack J. Mayo
Researcher in Machine Learning and Mathematical Statistics

Hi, and welcome to my page! I'm a forth-year PhD at the Korteweg-de Vries Institute for Mathematics at the University of Amsterdam. Under the supervision of Dr. Tim van Erven, I am currently working on the theory and mathematics underlying a broad class of decision-theoretic problems and modern machine learning methods.

My aim is to develop flexible, efficient and adaptive algorithms for online learning by drawing inspiration and techniques from information theory, mathematical statistics and (convex) optimization.

The aim is to achieve "out of the box" performance guarantees without the need for extensive hyperparameter tuning, ensuring adaptability across diverse machine learning domains while addressing robustness concerns and avoiding distributional assumptions wherever possible.

Topics of interest to me at present fall largely into the following categories:

- Parameter-free online learning.

- Connections between statistical learning and optimization methods.

- Bandits and Reinforcement learning.

I also have some work in nonequilibrium thermodynamics and condensed matter theory, from studies undertaken during my BSc and MSc.

Recent News;

January 7th 2024 - Very happy to be back TA'ig the Mastermath
course in Machine Learning Theory again (and this time in person)! If you're a math/machine learning student in the Netherlands curious about the foundations of machine learning, this course is highly recommended. 

December 18th 2023 - Back in Europe after an extended stay in North America, beginning with a research visit to Csaba Szepesvári and colleagues at the University of Alberta, Edmonton, and closing with a week-long stint in New Orleans for NeurIPS. Cheers to the Alberta group for being so accommodating, and the learning theory crowd for yet another unforgettable conference!

May 14th 2022 - The first paper of my PhD "Scale-free Unconstrained Online Learning for Curved Losses" (joint with Hedi and Tim) has been accepted to the 35th Annual Conference on Learning Theory (COLT 2022).

December 12th 2021 - Tim has remolded his statistical learning corpus into a new course at the UvA, entitled The Mathematics of Machine Learning, which I'll be TA'ing next semester!

January 26th 2021 - Very excited to be TA'ing the Mastermath course in Machine Learning Theory from February 11th 2021. Tim and Wouter have worked in some new and very current topics under the broad heading of online convex optimisation. Sign up at the above link!

January 26th 2021 - I am co-organizing this years NeurIPS Debriefing along with Tim, which takes place at the end of February 2021. If you're interested in presenting some work (either your own, or something you'd like to emphasize from the conference) feel free to get in contact!

 Old news:

October 5th 2020 - Our work on "Unravelling intra-aggregate structural disorder using single-molecule spectroscopy" was awarded with an Editor's Pick in Journal of the American Chemical Society!

June 17th 2020 - Our work entitled "Full Counting Statistics of Topological Defects after Crossing a Phase Transition" was awarded with an Editor's Choice in PRL!

June 17th 2020 - Smitha Vishveshwara from the University of Illinois at Urbana-Champaign wrote this nice article about our work on topological defects in Physics Magazine: Defect or No Defect: It’s a Toss Up!