Get Started
Home
Topics
Search
Library
Research questionHow can machine-learning models predict rare, large events in scale-free processes beyond the training data’s observed range?Large events in power-law processes are sparsely represented in training data, so models must infer behavior beyond the scales they have seen. Self-similarity may provide useful structure, but coarse-graining and anomalous scaling make that structure difficult to represent.
AI
Machine Learning
Research Paper
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.Learning and extrapolating scale-invariant processesThe evidence covers a two-dimensional fractional Gaussian field with linear dynamics and the Abelian sandpile model. It includes experiments with several neural architectures and an exact characterization of the linear case, focusing on spectral bias and coarse-grained representations; it does not establish performance on real-world earthquake or avalanche data.research paper · Sep 2, 2026
Related questions
How can scientific machine-learning models overcome optimization plateaus when their local linearized subspace permits greater accuracy?How can reliable foundation-model scaling laws be constructed without training every configuration?How can graph neural networks capture long-range interactions without oversmoothing or oversquashing on diverse large graphs?How can parametric PDE solution operators extrapolate to unseen regimes without failing silently?