L1 regularization of ReLU network weights is the most effective lever for speeding up mixed-integer optimization over the network, and there is a quantified trade-off between model redundancy and solver runtime.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An analysis of optimization problems involving ReLU neural networks
L1 regularization of ReLU network weights is the most effective lever for speeding up mixed-integer optimization over the network, and there is a quantified trade-off between model redundancy and solver runtime.