Hi, I'm Maxime. I'm a final-year PhD student in machine learning.
I am interested in using probabilistic machine learning for making decisions. In particular, how to effectively train, fine-tune or continually update neural networks using insights from deep learning theory and Bayesian deep learning; how to model arbitrary and complex distributions with neural density estimation; and how to reliably account for uncertainty and risk in model predictions using tools such as conformal prediction.
Some other topics and areas I work on include:
I am currently interning as a member of technical staff in an AI software development agents startup.
I write articles related to things I'm working on. Here are the latest ones:
An alternative Bayesian neural network prior, that we might believe a little more - but that sadly doesn’t work very well.
An overview of some recent work, published in ICLR 2024, where we estimate the uncertainty and marginal likelihoods in LLMs using Bayesian LoRA adapters. We focus on the fine-tuning setting, and scale our method to LLMs using a Laplace approximation with low-rank K-FAC.
A motivation of the Hessian from an optimisation perspective (and the related Generalised Gauss-Newton / Fisher Information Matrix), an introduction to Kronecker-factored approximate curvature, and applications of the curvature in machine learning.
Some papers I have written or co-authored.
Adam X. Yang, Maxime Robeyns, Thomas Coste, Jun Wang, Haitham Bou-Ammar, Laurence Aitchison
2024 – Pre-print
https://arxiv.org/pdf/2402.13210.pdf
Adam X. Yang, Maxime Robeyns, Xi Wang, Laurence Aitchison
2024 – ICLR
https://arxiv.org/abs/2308.13111
Michele Garibbo, Maxime Robeyns, Laurence Aitchison
2023 – NeurIPS
https://arxiv.org/abs/2302.14182
Adam X. Yang, Maxime Robeyns, Edward Milsom, Nandi Schoots, Laurence Aitchison
2023 – ICML
https://proceedings.mlr.press/v202/yang23k/yang23k.pdf
Maxime Robeyns, Sotiria Fotopolou, Mike Walmsley, Laurence Aitchison
2022 – ICML 2022 Workshop on Machine Learning for Astrophysics
https://ml4astro.github.io/icml2022/assets/12.pdf
Any other drivel and shower thoughts end up in my "fragments". Here are the last ones: