New ML models tackle prediction of rare, large-scale events

Researchers have developed new machine learning models, including a Fourier-Mellin Neural Operator and a wavelet-decomposition based Graph Neural Network, to address the challenge of predicting rare, large-scale events in self-similar processes. These models aim to improve extrapolation capabilities for phenomena like earthquakes and avalanches, which exhibit power-law behavior. Experiments with various architectures, such as U-Net and Riesz networks, were conducted to identify spectral biases and coarse-graining issues, with proposed solutions focusing on incorporating scale invariance as an inductive bias. AI

IMPACT Introduces novel ML architectures for predicting rare events, potentially advancing scientific modeling in fields like seismology and materials science.

RANK_REASON The cluster contains a research paper detailing new machine learning models and experiments. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• cs.LG
• Fourier embedding layer
• Fourier-Mellin Neural Operator
• François Landes
• graph neural network
• language
• machine learning
• Riesz network
• U-Net
• visual perception

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →