A backpropagation-free training approach for Hamiltonian neural networks via data-driven parameter sampling that claims over 100x CPU speedup and four orders of magnitude better accuracy on chaotic systems like Hénon-Heiles compared to gradient-based methods.
Pytorch: An imperative style, high-performance deep learning library
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2024 2representative citing papers
CSMC integrates column subset selection with low-rank matrix completion to reduce computation for asymmetric incomplete matrices while claiming competitive accuracy on synthetic and real tasks.
citing papers explorer
-
Training Hamiltonian neural networks without backpropagation
A backpropagation-free training approach for Hamiltonian neural networks via data-driven parameter sampling that claims over 100x CPU speedup and four orders of magnitude better accuracy on chaotic systems like Hénon-Heiles compared to gradient-based methods.
-
Randomized Approach to Matrix Completion: Applications in Recommendation Systems and Image Inpainting
CSMC integrates column subset selection with low-rank matrix completion to reduce computation for asymmetric incomplete matrices while claiming competitive accuracy on synthetic and real tasks.