Closed-form rank-constrained linear estimators, derived from Bayes risk, unify forward modeling, inverse recovery, autoencoding, and denoising, and often match or beat trained neural networks.
Exact representation and efficient approximations of linear model predictive control laws via HardTanh type deep neural networks
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
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Optimal Linear Baseline Models for Scientific Machine Learning
Closed-form rank-constrained linear estimators, derived from Bayes risk, unify forward modeling, inverse recovery, autoencoding, and denoising, and often match or beat trained neural networks.