Aaron J.
Havens
Postdoctoral Researcher
Meta Fundamental AI Research (FAIR)
I’m a postdoctoral researcher at FAIR on the Generative Modeling Foundations team under Brian Karrer and Yaron Lipman. I’m developing scalable methods for generative modeling and principled reward-based tilting / finetuning in both continuous and discrete domains. I’m especially passionate about modeling physical processes that help advance Engineering and science, taking into account geometric structures and invariants.
Previously I received a PhD in ECE from University of Illinois Urbana-Champaign, where I worked on robust control theory $\cap$ machine learning under Prof. Bin Hu. I also have an MS in Aerospace Engineering from UIUC where I primarily worked on learning algorithms for autonomous field-robotics under Prof. Girish Chowdhary. I’ve been fortunate to have several industry research experiences at Meta FAIR NYC, Peferred Networks Tokyo, TuSimple (autonomous semi-trucks) and NASA Jet Propulsion Lab (JPL).
I’m orignally from Des Moines, Iowa 🌽 and earned my Bachelors in Mechanical Engineering at Iowa State University, Ames, Iowa.
selected publications
- ICMLFine-grained local sensitivity analysis of standard dot-product self-attentionIn Forty-first International Conference on Machine Learning, 2024
- ICLROn the scalability and memory efficiency of semidefinite programs for lipschitz constant estimation of neural networksIn , 2024
- ICLRNovel Quadratic Constraints for Extending LIPSDP Beyond Slope-restricted ActivationsIn 12th International Conference on Learning Representations, 2024
- L4DC
Forced variational integrator networks for prediction and control of mechanical systemsIn Learning for Dynamics and Control, 2021 - NeurIPS
Online robust policy learning in the presence of unknown adversariesAdvances in neural information processing systems, 2018