Reproduce “Multi-Task Learning of Conditional Mean Operators: applications to dynamical systems and uncertainty quantification” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sami Chemlal, Thibaut Germain, Rémi Flamary, Vladimir R. Kostic, Karim Lounici
The authors develop MTL-CMO, learning shared function spaces across related simulations while retaining task-specific operators, then fitting an operator for a new system in closed form. In simulated Tokam2D plasma trajectories, its spectrum supports regression of two parameters using labeled examples: on 80 held-out systems with 4,093 frames, R² is 0.932 for g and 0.992 for κ, above pooled NCP.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.