A log-sum-exp mixture of input-convex neural networks fits multi-well potentials with learnable transition sharpness and sparse mode discovery.
The development of transition-state theory
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Differentiable neural network representation of multi-well, locally-convex potentials
A log-sum-exp mixture of input-convex neural networks fits multi-well potentials with learnable transition sharpness and sparse mode discovery.