Showing 2024Show all
2 papers · 1 filter
cs.LG2024
Improving Discrete Optimisation Via Decoupled Straight-Through Estimator
Rushi Shah, Mingyuan Yan, Michael Curtis Mozer +1
The Straight-Through Estimator (STE) is the dominant method for training neural networks with discrete variables, enabling gradient-based optimisation by routing gradients through…
cs.LG2024
Initialization-enhanced Physics-Informed Neural Network with Domain Decomposition (IDPINN)
Chenhao Si, Ming Yan
We propose a new physics-informed neural network framework, IDPINN, based on the enhancement of initialization and domain decomposition to improve prediction accuracy. We train a P…